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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "throw" and related actions or contexts involving throwing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chré
    -0.79
     grotte
    -0.75
     independientes
    -0.74
     scolaires
    -0.74
     particulières
    -0.73
    cog
    -0.73
    essentiel
    -0.71
     huellas
    -0.70
     vallée
    -0.69
    endregion
    -0.68
    POSITIVE LOGITS
     throw
    1.90
     throwing
    1.68
     throws
    1.67
     Throw
    1.66
     thrown
    1.62
     threw
    1.62
    throwing
    1.53
    Throw
    1.48
     Throwing
    1.47
    thrown
    1.42
    Act Density 0.076%

    No Known Activations