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

    Neuronpedia

    INDEX
    Explanations

    references to the word "crack" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fédé
    -0.49
    <?
    -0.48
     propOrder
    -0.45
    뀔
    -0.44
     dieß
    -0.44
     Савезне
    -0.43
    aarrggbb
    -0.43
     ejus
    -0.43
    ovací
    -0.42
     zlo
    -0.41
    POSITIVE LOGITS
     crack
    0.67
     Crack
    0.63
     averages
    0.62
    crack
    0.61
     preference
    0.59
     average
    0.59
     tendency
    0.59
     CRACK
    0.57
    平均
    0.56
     bias
    0.55
    Act Density 1.534%

    No Known Activations