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

    Neuronpedia

    INDEX
    Explanations

    negative instructions or prohibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msgSender
    -0.62
    __*/
    -0.47
     intptr
    -0.45
    AxisAlignment
    -0.44
    ::$_
    -0.42
     living
    -0.42
     _$
    -0.40
    atiker
    -0.40
     pang
    -0.40
    bf
    -0.40
    POSITIVE LOGITS
     مرئيه
    0.80
     للمعارف
    0.72
     виправивши
    0.71
     utafitiHapana
    0.64
     Peraturan
    0.61
    BibitemShut
    0.60
    )">
    0.60
    Pgina
    0.59
     sceptre
    0.59
     HasFactory
    0.59
    Act Density 0.198%

    No Known Activations