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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software development and programming

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to software development and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schne
    -0.64
     Cotton
    -0.64
    ELD
    -0.63
     negatives
    -0.61
    ERO
    -0.60
     Sins
    -0.59
     Downs
    -0.59
     ANG
    -0.59
     Ninth
    -0.58
     Wright
    -0.58
    POSITIVE LOGITS
    _
    1.23
    wagen
    0.89
    _(
    0.89
    /)
    0.87
    __
    0.84
    @
    0.79
    _.
    0.77
    ensis
    0.76
    /.
    0.76
    ['
    0.75
    Act Density 0.164%

    No Known Activations