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

    Neuronpedia

    INDEX
    Explanations

    words related to the need for someone or something in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    roles and titles associated with leadership or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.63
    aves
    -0.63
    ighters
    -0.63
    76561
    -0.62
     batches
    -0.59
     excerpts
    -0.59
    ests
    -0.58
     distances
    -0.58
    inders
    -0.58
     contents
    -0.58
    POSITIVE LOGITS
     willing
    1.06
     capable
    0.93
     whom
    0.91
     suitable
    0.88
     who
    0.85
    hunt
    0.84
     named
    0.82
     whose
    0.78
     persona
    0.77
     overseeing
    0.77
    Act Density 0.332%

    No Known Activations