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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to data handling and programming issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Morrow
    -0.16
    KR
    -0.15
    NCY
    -0.15
     Slut
    -0.14
    acle
    -0.14
    icap
    -0.14
     tender
    -0.14
    Slf
    -0.14
     Moff
    -0.14
     Salisbury
    -0.13
    POSITIVE LOGITS
     Rad
    0.35
     rad
    0.32
    .Rad
    0.32
    Rad
    0.32
    .rad
    0.28
    -rad
    0.26
     Radical
    0.26
    _rad
    0.25
    rad
    0.25
     radial
    0.24
    Act Density 0.008%

    No Known Activations