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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with actions taken over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ij士
    -0.65
    BuyableInstoreAndOnline
    -0.63
     advoc
    -0.62
     destro
    -0.61
     rall
    -0.59
     Tot
    -0.59
     rul
    -0.58
     Miko
    -0.58
     Citiz
    -0.54
     slic
    -0.54
    POSITIVE LOGITS
    .
    0.96
    .</
    0.94
     nowadays
    0.92
     ().
    0.91
    .—
    0.91
    .(
    0.91
    .–
    0.91
    .<
    0.88
    .[
    0.86
    ;
    0.86
    Act Density 0.143%

    No Known Activations