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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to taking action or making significant decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongo
    -0.75
    amation
    -0.70
    Weather
    -0.70
    uppet
    -0.66
    ongyang
    -0.63
    Origin
    -0.63
    FX
    -0.62
    nesota
    -0.61
    Ter
    -0.61
    Vari
    -0.60
    POSITIVE LOGITS
     anew
    0.98
    strip
    0.87
     again
    0.85
     whereby
    0.80
     wisely
    0.80
     unilaterally
    0.79
     responsibly
    0.78
     willingly
    0.77
    naires
    0.76
     reluctantly
    0.76
    Act Density 0.267%

    No Known Activations