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

    Neuronpedia

    INDEX
    Explanations

    phrases related to warnings and indications of risk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     переписи
    -0.54
    setImageBitmap
    -0.52
    StructEnd
    -0.52
    stination
    -0.51
    InjectAttribute
    -0.50
    uality
    -0.48
     تانيه
    -0.46
    сшта
    -0.46
    hirts
    -0.46
     Egli
    -0.46
    POSITIVE LOGITS
    OGND
    0.64
    Autoritní
    0.61
     كومونز
    0.60
     consultato
    0.58
    defer
    0.58
    ][]
    0.57
    cplusplus
    0.55
    verifyException
    0.54
    Datuak
    0.53
    sizeCache
    0.51
    Act Density 0.280%

    No Known Activations