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

    Neuronpedia

    INDEX
    Explanations

    terms related to scoring and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AlterField
    -0.75
     препратки
    -0.73
    =""/>
    -0.73
     onCancelled
    -0.71
     hinein
    -0.68
    liesslich
    -0.68
    Hyde
    -0.68
    omiast
    -0.67
    ugd
    -0.67
    zewod
    -0.66
    POSITIVE LOGITS
     scores
    2.07
     score
    2.02
     Scores
    1.89
     scored
    1.85
     Score
    1.79
     scoring
    1.75
    score
    1.70
    scores
    1.69
    Scores
    1.69
    Score
    1.67
    Act Density 0.031%

    No Known Activations