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

    Neuronpedia

    INDEX
    Explanations

    sentences articulating strong opinions or emphasizing specific points

    oai_token-act-pair · gpt-3.5-turbo

    the word "just" and its repeated use in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidx
    -0.76
     sacrific
    -0.69
     seiz
    -0.66
     Also
    -0.61
    essor
    -0.61
    anwhile
    -0.61
    ynasty
    -0.60
     destro
    -0.59
    abulary
    -0.59
     necks
    -0.59
    POSITIVE LOGITS
    ifiable
    1.30
    ifications
    1.05
     plain
    0.98
    if
    0.86
     kidding
    0.85
     icing
    0.84
    ified
    0.83
    IFIED
    0.83
     desserts
    0.82
    IFIC
    0.75
    Act Density 0.092%

    No Known Activations