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

    Neuronpedia

    INDEX
    Explanations

    terms related to political and social issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to authority, community, and leadership figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.63
    font
    -0.63
    tnc
    -0.61
    omatic
    -0.60
    ATER
    -0.59
    rossover
    -0.57
    taining
    -0.57
     Brow
    -0.56
    apan
    -0.56
    cit
    -0.55
    POSITIVE LOGITS
     reacted
    0.97
     chose
    0.91
     opted
    0.89
     threw
    0.88
     responded
    0.86
     recognized
    0.85
     recognizes
    0.85
     undertook
    0.85
     succeeded
    0.84
     intervened
    0.83
    Act Density 0.828%

    No Known Activations