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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific limits or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĹı
    -0.17
    yum
    -0.15
    ison
    -0.15
    ean
    -0.15
    udo
    -0.15
     Moff
    -0.14
    ITUDE
    -0.14
    ynth
    -0.14
    ifo
    -0.14
     syn
    -0.13
    POSITIVE LOGITS
    odore
    0.17
    baugh
    0.17
    edReader
    0.16
    enstein
    0.16
    RD
    0.15
    igne
    0.15
    istrovstvÃŃ
    0.15
    _PAYLOAD
    0.15
    957
    0.15
    utom
    0.15
    Act Density 0.004%

    No Known Activations