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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal emotions and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.72
    __;
    -0.66
     HasFactory
    -0.65
     tslint
    -0.64
     Majefty
    -0.63
    Xna
    -0.62
    innung
    -0.62
     ſche
    -0.60
    BufferException
    -0.60
     houſe
    -0.60
    POSITIVE LOGITS
    ⓧ
    0.52
    évaluateur
    0.49
    よ
    0.46
    ğim
    0.45
    GOTREF
    0.44
     k
    0.42
     sauce
    0.42
    ube
    0.41
     G
    0.41
    <eos>
    0.41
    Act Density 0.107%

    No Known Activations