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

    Neuronpedia

    INDEX
    Explanations

    instances where something or someone transitions or progresses in some way

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "go from" indicating transitions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QUI
    -0.74
    lied
    -0.72
    perture
    -0.70
    vic
    -0.69
    iosyn
    -0.68
    ascript
    -0.68
    must
    -0.67
    ounce
    -0.67
    quote
    -0.65
    Flags
    -0.65
    POSITIVE LOGITS
     afar
    0.86
     whence
    0.76
     Albania
    0.67
     obscurity
    0.65
     exhaustion
    0.64
     kindergarten
    0.63
     somewhere
    0.63
     scratch
    0.62
     unrecogn
    0.61
     adolescence
    0.60
    Act Density 0.064%

    No Known Activations