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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety and vulnerability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.99
     Efq
    -0.75
     שוליים
    -0.74
    BufferException
    -0.73
     InputDecoration
    -0.73
     uſed
    -0.72
     للمعارف
    -0.70
    LookAnd
    -0.70
    kheim
    -0.69
    ViewFeatures
    -0.69
    POSITIVE LOGITS
     terkena
    0.49
     menerapkan
    0.48
     concernés
    0.46
     participating
    0.45
     segno
    0.44
    Participating
    0.42
     affected
    0.42
    対象
    0.42
    にかけて
    0.41
    affected
    0.40
    Act Density 0.812%

    No Known Activations