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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms indicating references and attributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nt
    -0.18
    la
    -0.16
    _DEPRECATED
    -0.14
    ÑİÑĢ
    -0.13
    antaged
    -0.13
    ico
    -0.13
    agger
    -0.13
    tractive
    -0.13
    ä½
    -0.12
    uo
    -0.12
    POSITIVE LOGITS
    aida
    0.15
    forth
    0.14
    ably
    0.14
    itoris
    0.14
    Ł³
    0.14
    rosso
    0.14
    -ı
    0.14
    umat
    0.14
    imb
    0.14
    lessly
    0.14
    Act Density 0.083%

    No Known Activations