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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to matching and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.94
     généraux
    -0.91
    quirrel
    -0.89
    Vader
    -0.82
    hehehe
    -0.81
    zzleHttp
    -0.80
     Geller
    -0.78
     autorytatywna
    -0.77
    toluene
    -0.75
    Demikian
    -0.75
    POSITIVE LOGITS
     MATCH
    1.55
     Match
    1.47
    MATCH
    1.45
     match
    1.45
     matches
    1.45
    Match
    1.40
     Matches
    1.36
    match
    1.35
    matches
    1.29
    Matches
    1.19
    Act Density 0.065%

    No Known Activations