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

    Neuronpedia

    INDEX
    Explanations

    versions and numerical identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thu
    -0.18
    584
    -0.18
    540
    -0.16
    ender
    -0.16
    avou
    -0.15
     eldre
    -0.14
    526
    -0.14
    528
    -0.14
    IED
    -0.14
    abor
    -0.14
    POSITIVE LOGITS
    구
    0.15
    oftware
    0.15
    enou
    0.15
    _GB
    0.14
    enk
    0.14
     cih
    0.14
     tòa
    0.14
    обов
    0.14
    ç¬Ķ
    0.14
    IZE
    0.14
    Act Density 0.243%

    No Known Activations