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

    Neuronpedia

    INDEX
    Explanations

    explicit references to positivity and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ẽ
    -0.15
    sav
    -0.15
    bach
    -0.15
    ikki
    -0.15
    ships
    -0.15
     pozor
    -0.14
    bine
    -0.14
    layer
    -0.14
    icom
    -0.14
    NAMESPACE
    -0.14
    POSITIVE LOGITS
    /n
    0.26
    -negative
    0.22
    -sum
    0.21
    _INFINITY
    0.20
    -feedback
    0.20
    IntegerField
    0.20
     reinforcement
    0.19
    itives
    0.19
     feedback
    0.18
    /N
    0.18
    Act Density 0.030%

    No Known Activations