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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "broken."

    oai_token-act-pair · gpt-3.5-turbo

    the word "broken" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minist
    -0.87
    anamo
    -0.84
    utra
    -0.83
    urai
    -0.83
    ittee
    -0.76
    itatively
    -0.73
    azor
    -0.73
    udic
    -0.73
    yss
    -0.72
    aeda
    -0.72
    POSITIVE LOGITS
    hearted
    0.93
    neck
    0.91
     bones
    0.83
    bones
    0.81
     ribs
    0.76
     necks
    0.74
    adoes
    0.73
    broken
    0.73
     hearts
    0.72
    heart
    0.71
    Act Density 0.031%

    No Known Activations