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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the strength or intensity of actions or states

    oai_token-act-pair · gpt-3.5-turbo

    references to governance or procedural issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behavi
    -0.77
    ulence
    -0.74
     tremend
    -0.67
    reality
    -0.65
    lihood
    -0.63
     ethics
    -0.63
    figure
    -0.62
     neigh
    -0.62
    NESS
    -0.62
     relent
    -0.62
    POSITIVE LOGITS
    pleted
    1.15
     Played
    1.12
    ired
    1.12
    iked
    1.07
    ried
    1.07
    arthed
    1.05
    asted
    1.04
    Used
    1.03
     Bought
    1.02
    Posted
    1.01
    Act Density 0.229%

    No Known Activations