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

    Neuronpedia

    INDEX
    Explanations

    phrases related to breaking or cracking something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "crack," "cracked," and "cracking" indicating breakage or disruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikk
    -0.72
    enture
    -0.69
    folk
    -0.68
    alla
    -0.67
    endment
    -0.65
     Leth
    -0.64
     Columb
    -0.62
    gard
    -0.62
     attention
    -0.62
    anders
    -0.60
    POSITIVE LOGITS
    pots
    1.15
     cracking
    0.88
    kered
    0.86
    ibly
    0.78
    pot
    0.76
    Berry
    0.76
     cracks
    0.75
     jaws
    0.75
    lings
    0.74
    vine
    0.73
    Act Density 0.010%

    No Known Activations