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

    Neuronpedia

    INDEX
    Explanations

    adjectives or nouns related to foundational principles or root causes

    oai_token-act-pair · gpt-3.5-turbo

    references to underlying causes, issues, or factors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aido
    -0.90
    helm
    -0.79
    uba
    -0.77
     Sabha
    -0.76
    udo
    -0.76
    hops
    -0.76
    urate
    -0.75
    asia
    -0.74
    zanne
    -0.73
    hire
    -0.73
    POSITIVE LOGITS
     premise
    1.35
     principle
    1.32
     principles
    1.29
     assumption
    1.24
     rationale
    1.24
     structure
    1.21
     theme
    1.20
     tenets
    1.19
     underlying
    1.18
     motivations
    1.16
    Act Density 0.082%

    No Known Activations