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

    Neuronpedia

    INDEX
    Explanations

    terms related to ranking or evaluation processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     kohdetta
    -0.88
    Билгалдахарш
    -0.86
     itſelf
    -0.83
     PLW
    -0.83
    coaster
    -0.83
    évaluateur
    -0.82
    ThroughAttribute
    -0.81
     _('
    -0.80
     Wexford
    -0.79
     Drog
    -0.78
    POSITIVE LOGITS
     RANK
    1.52
     Rank
    1.45
    Rank
    1.42
    rank
    1.41
    RANK
    1.40
     rank
    1.39
     ranks
    1.33
     Ranks
    1.31
     Rankin
    1.29
    ranks
    1.27
    Act Density 0.012%

    No Known Activations