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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations or logical constructs

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    InitStructure
    -0.60
    ımıza
    -0.59
     your
    -0.57
    路
    -0.57
     Duval
    -0.56
    なんでも
    -0.56
    ru
    -0.55
     pronta
    -0.55
     ready
    -0.54
     åt
    -0.54
    POSITIVE LOGITS
    –
    1.12
     myſelf
    1.06
     himſelf
    0.97
     fevere
    0.94
     Mino
    0.90
     ſtate
    0.89
    extAlignment
    0.87
    ✨:
    0.87
     ſever
    0.86
     numberWith
    0.85
    Act Density 0.000%

    No Known Activations