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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the initiation or start of an action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the initiation of actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.70
    iasco
    -0.64
     Explosion
    -0.62
    ItemTracker
    -0.62
    lihood
    -0.61
    ãĤ´ãĥ³
    -0.61
     Seym
    -0.60
    typ
    -0.59
     caveat
    -0.58
     Viz
    -0.57
    POSITIVE LOGITS
     purposes
    0.71
    uate
    0.67
    ().
    0.64
     Ratio
    0.62
     efficiently
    0.62
    fill
    0.60
    ansky
    0.60
    inton
    0.60
     rid
    0.58
     ratio
    0.58
    Act Density 0.432%

    No Known Activations