Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and emotions related to community and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    intensified evaluative descriptors—adjectives/adverbs conveying strong degree or notable qualities like complexity, uniqueness, severity, or chaos.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.74
    \{\\
    -0.65
     الرياضيه
    -0.59
    estacks
    -0.56
     برانيه
    -0.55
    InitVars
    -0.54
    NamedQueries
    -0.52
    MigrationBuilder
    -0.52
    InitStruct
    -0.50
    InputTagHelper
    -0.50
    POSITIVE LOGITS
    非常好
    0.42
    -------
    0.38
     indeed
    0.38
     concerning
    0.38
    aronder
    0.37
    issima
    0.37
    íssima
    0.37
     regarding
    0.36
     للغاية
    0.36
    меется
    0.36
    Act Density 0.782%

    No Known Activations