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

    Neuronpedia

    INDEX
    Explanations

    terms associated with matching or comparisons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.95
     généraux
    -0.91
    quirrel
    -0.90
    zzleHttp
    -0.88
    Vader
    -0.84
    hehe
    -0.78
    hehehe
    -0.78
    Demikian
    -0.78
     Geller
    -0.76
    toluene
    -0.76
    POSITIVE LOGITS
     MATCH
    1.70
     Match
    1.59
     match
    1.55
    MATCH
    1.54
     matches
    1.53
    Match
    1.50
     Matches
    1.44
    match
    1.43
    matches
    1.32
    Matches
    1.24
    Act Density 0.056%

    No Known Activations