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

    Neuronpedia

    INDEX
    Explanations

    phrases related to beginning or starting something

    oai_token-act-pair · gpt-3.5-turbo

    references to starting actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.64
    osponsors
    -0.62
    arians
    -0.59
    abytes
    -0.59
    itsch
    -0.57
    cko
    -0.57
    mens
    -0.57
    Param
    -0.57
    ب
    -0.57
    mean
    -0.56
    POSITIVE LOGITS
     countdown
    0.97
     fray
    0.92
     anew
    0.90
     process
    0.85
     bleeding
    0.82
     dialogue
    0.79
     journey
    0.78
     conversation
    0.74
     hostilities
    0.73
     discussion
    0.71
    Act Density 0.099%

    No Known Activations