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

    Neuronpedia

    INDEX
    Explanations

    terms related to damage or harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Oasis
    -0.15
    gebn
    -0.15
    illez
    -0.14
    ãģ£ãģ¡
    -0.14
    ITA
    -0.14
    iteit
    -0.14
    linger
    -0.14
    zeitig
    -0.14
    ICT
    -0.13
    332
    -0.13
    POSITIVE LOGITS
    ion
    1.03
    ions
    0.81
    ION
    0.77
    ioned
    0.65
    iona
    0.63
     ion
    0.63
    -ion
    0.62
    ioni
    0.61
    ione
    0.57
    Ion
    0.57
    Act Density 0.042%

    No Known Activations