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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing positive evaluation or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.56
    JsonPropertyName
    -0.54
    Angus
    -0.52
    getAction
    -0.52
    Dario
    -0.49
     HasFactory
    -0.47
    apatalk
    -0.46
    Alexandre
    -0.46
     Lanz
    -0.46
    afficheront
    -0.46
    POSITIVE LOGITS
    Well
    1.11
     Well
    1.07
    well
    1.01
     well
    1.00
     WELL
    0.93
    WELL
    0.87
     Wells
    0.71
     wel
    0.69
     wells
    0.69
     Wel
    0.65
    Act Density 0.080%

    No Known Activations