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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to scoring or evaluation metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isnan
    -0.80
    =""/>
    -0.80
    Gweler
    -0.77
     onCancelled
    -0.73
    zewod
    -0.73
    }">
    -0.70
    Hyde
    -0.70
     препратки
    -0.70
    AlterField
    -0.69
     Hyde
    -0.69
    POSITIVE LOGITS
     scores
    1.57
     Scores
    1.49
     score
    1.44
     scored
    1.43
     Score
    1.34
    Scores
    1.31
     scoring
    1.30
     SCORE
    1.29
    scores
    1.26
     Scor
    1.21
    Act Density 0.044%

    No Known Activations