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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking actions or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions or intentions related to doing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.72
    è¦ļéĨĴ
    -0.65
    uras
    -0.65
    cosystem
    -0.65
    emonic
    -0.63
    osure
    -0.62
    athering
    -0.60
    mingham
    -0.60
    ORPG
    -0.60
    =~=~
    -0.59
    POSITIVE LOGITS
     tomorrow
    0.98
     hereafter
    0.91
     someday
    0.89
     whatever
    0.82
     gladly
    0.82
     whoever
    0.79
     thee
    0.76
     whichever
    0.76
     soon
    0.74
     if
    0.73
    Act Density 0.430%

    No Known Activations