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

    Neuronpedia

    INDEX
    Explanations

    terms related to ranking and classification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gön
    -0.82
    ThroughAttribute
    -0.74
    /*
    -0.73
     onPostExecute
    -0.71
     kohdetta
    -0.71
     _('
    -0.70
    Closer
    -0.69
    Activator
    -0.69
    riwal
    -0.69
    ätzlich
    -0.67
    POSITIVE LOGITS
     RANK
    1.70
     rank
    1.57
     Rank
    1.56
     ranks
    1.56
    rank
    1.53
    Rank
    1.52
     Ranks
    1.48
    RANK
    1.46
     ranking
    1.44
     Rankin
    1.41
    Act Density 0.122%

    No Known Activations