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

    Neuronpedia

    INDEX
    Explanations

    instances where someone or something is interested in a particular topic or activity

    oai_token-act-pair · gpt-3.5-turbo

    instances of interest or involvement in various topics or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lag
    -0.72
    minus
    -0.70
     reluct
    -0.69
    ERROR
    -0.68
    uid
    -0.66
     guiActiveUn
    -0.65
    falls
    -0.64
    soever
    -0.63
    Dispatch
    -0.63
    CN
    -0.62
    POSITIVE LOGITS
     preserving
    0.96
     keeping
    0.88
    clus
    0.84
     pursuing
    0.79
     maintaining
    0.76
     academia
    0.76
    clusions
    0.73
    politics
    0.72
     helping
    0.68
    ysics
    0.68
    Act Density 0.068%

    No Known Activations