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

    Neuronpedia

    INDEX
    Explanations

    words that describe strength or impact

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    -
    -0.70
    E
    -0.67
    T
    -0.65
    C
    -0.59
    e
    -0.58
     T
    -0.57
    N
    -0.56
     E
    -0.56
    R
    -0.56
     chroma
    -0.55
    POSITIVE LOGITS
     Powerful
    1.11
    Powerful
    1.11
     potent
    1.06
     puissante
    1.02
    potent
    1.01
    bibinfo
    0.94
     puissant
    0.93
     ་་
    0.91
     myſelf
    0.87
    BibitemShut
    0.87
    Act Density 0.007%

    No Known Activations