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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "throw" and its variations, emphasizing actions related to throwing objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.76
     chré
    -0.72
     huellas
    -0.71
    essentiel
    -0.71
    ADEL
    -0.71
     particulières
    -0.71
    diale
    -0.70
     scolaires
    -0.70
     grotte
    -0.70
     fidèles
    -0.70
    POSITIVE LOGITS
     throw
    1.72
     Throw
    1.55
     throwing
    1.52
     throws
    1.49
     threw
    1.47
     thrown
    1.46
    Throw
    1.39
    throwing
    1.38
     Throwing
    1.34
    throws
    1.33
    Act Density 0.083%

    No Known Activations