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

    Neuronpedia

    INDEX
    Explanations

    exclamatory greetings or informal conversational openings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     trebui
    -0.69
    oficina
    -0.66
    quiao
    -0.66
    ArgsConstructor
    -0.64
     Brasileiro
    -0.63
    aero
    -0.61
     Thorpe
    -0.60
    rungsseite
    -0.59
     HasFactory
    -0.58
    TagMode
    -0.58
    POSITIVE LOGITS
     HEY
    1.10
     Hey
    1.05
    Hey
    1.02
     hey
    0.98
    HEY
    0.93
    hey
    0.90
     Heywood
    0.82
    +/**
    0.80
     Hei
    0.79
     Heide
    0.71
    Act Density 0.002%

    No Known Activations