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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and references to specific individuals or cases

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     compris
    -0.49
     comod
    -0.48
     F
    -0.45
    lo
    -0.44
    inter
    -0.44
    pla
    -0.42
    cur
    -0.42
     IS
    -0.41
    ospel
    -0.41
    ф
    -0.41
    POSITIVE LOGITS
    +#+#
    1.09
     Signalez
    1.07
    Autoritní
    1.02
     ***!
    0.97
    InjectAttribute
    0.94
    RectangleBorder
    0.92
     kaarangay
    0.91
    ंदीखरीदारी
    0.89
    URLException
    0.89
     Normdatei
    0.89
    Act Density 0.507%

    No Known Activations