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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to safety and health concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioni
    -0.15
    achu
    -0.14
    aber
    -0.14
    Äįit
    -0.14
    871
    -0.14
    ickness
    -0.14
    oin
    -0.14
    ÂĿ
    -0.14
    833
    -0.13
    aza
    -0.13
    POSITIVE LOGITS
    loquent
    0.18
     Fet
    0.15
    ismatic
    0.15
    KeyCode
    0.15
     repair
    0.15
    rc
    0.15
    less
    0.14
     Gle
    0.14
    ARRANT
    0.14
    aceous
    0.14
    Act Density 0.158%

    No Known Activations