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

    Neuronpedia

    INDEX
    Explanations

    words related to presenting ideas or plans

    oai_token-act-pair · gpt-3.5-turbo

    terms related to proposals and requests in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccording
    -0.71
    Åį
    -0.69
    iliated
    -0.69
    aundering
    -0.69
    ecause
    -0.68
    everal
    -0.67
    hovah
    -0.67
    orks
    -0.66
    onen
    -0.64
    ategory
    -0.64
    POSITIVE LOGITS
     spree
    0.85
    fulness
    0.79
    iques
    0.71
    steps
    0.69
    ings
    0.68
     regarding
    0.67
     selections
    0.66
     exploits
    0.66
     rampage
    0.65
     blindness
    0.65
    Act Density 0.285%

    No Known Activations