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

    Neuronpedia

    INDEX
    Explanations

    financial and numerical data presented in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and numerical data related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edly
    -0.88
     ens
    -0.77
    emo
    -0.69
    THING
    -0.67
    issance
    -0.66
    ella
    -0.64
    fuck
    -0.61
    rang
    -0.60
    stuff
    -0.60
    Factor
    -0.60
    POSITIVE LOGITS
    versions
    1.04
     conjunction
    1.04
     favor
    1.03
     accordance
    1.02
    verts
    0.99
     increments
    0.98
     total
    0.98
     spite
    0.93
    animate
    0.92
     comparison
    0.91
    Act Density 0.164%

    No Known Activations