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

    Neuronpedia

    INDEX
    Explanations

    elements associated with distinctive or recognizable characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipe
    -0.18
    çīĩ
    -0.15
    hlen
    -0.14
    ape
    -0.14
    roken
    -0.14
    ffset
    -0.14
    олÑĮз
    -0.14
    emb
    -0.14
    icias
    -0.13
    ç½²
    -0.13
    POSITIVE LOGITS
    trag
    0.15
    arat
    0.14
     Gow
    0.14
    urum
    0.14
    locals
    0.14
     Maiden
    0.13
    thinkable
    0.13
    iž
    0.13
    avian
    0.13
    555
    0.13
    Act Density 0.239%

    No Known Activations