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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    words related to initiating or carrying out actions or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     voic
    -0.75
     ric
    -0.75
     bullets
    -0.74
     flavor
    -0.73
     center
    -0.71
     humor
    -0.70
     jokes
    -0.68
     rhythm
    -0.67
     cool
    -0.67
     ping
    -0.66
    POSITIVE LOGITS
     undertaking
    2.82
     undertake
    2.78
     undertaken
    2.46
     undertook
    2.28
     embark
    1.88
     embarked
    1.65
     endeavour
    1.61
     undert
    1.57
     endeav
    1.22
     endeavor
    1.11
    Act Density 0.026%

    No Known Activations