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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    sentences indicating attempts or commitments to take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Roman
    -0.72
    ritical
    -0.68
    Definition
    -0.67
    catentry
    -0.66
    esan
    -0.65
    ullah
    -0.65
    Vers
    -0.64
    quart
    -0.64
    Recent
    -0.62
    Pi
    -0.62
    POSITIVE LOGITS
    anmar
    0.72
    IVERS
    0.65
    icate
    0.63
     plenty
    0.62
    ãĥ¼
    0.62
     thee
    0.61
     tune
    0.60
     remem
    0.60
    Ĥ¬
    0.60
     partName
    0.59
    Act Density 0.084%

    No Known Activations