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

    Neuronpedia

    INDEX
    Explanations

    concepts related to internal conflicts and emotional struggles

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

    before periods, "and," "to," or "that"

    np_acts-logits-general · gemini-2.0-flash

    decision outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     But
    -0.60
     pero
    -0.55
    但她
    -0.52
     maupun
    -0.50
    But
    -0.50
    tels
    -0.50
    pero
    -0.48
     aber
    -0.48
    but
    -0.48
     plus
    -0.47
    POSITIVE LOGITS
    Personendaten
    0.77
    AnchorStyles
    0.75
    RegressionTest
    0.74
    IsMutable
    0.74
    bootstrapcdn
    0.72
     asupra
    0.71
     Jefus
    0.70
     Efq
    0.70
     AspNetCore
    0.69
     Majefty
    0.69
    Act Density 0.534%

    No Known Activations