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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to things that are cracked

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cracked" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amins
    -0.71
    alla
    -0.70
    enture
    -0.68
    folk
    -0.67
    ikk
    -0.66
    ¥µ
    -0.65
     Vanguard
    -0.64
     Dayton
    -0.63
    ista
    -0.63
    DK
    -0.63
    POSITIVE LOGITS
     cracking
    1.10
    pots
    1.08
     cracked
    1.06
     cracks
    0.87
     jaws
    0.85
    estamp
    0.79
    kered
    0.79
     crack
    0.76
    Berry
    0.74
    breakers
    0.73
    Act Density 0.008%

    No Known Activations