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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating safety concerns or legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nen
    -0.16
    ī
    -0.15
    alus
    -0.15
    rones
    -0.14
    berger
    -0.14
    ÑĢеб
    -0.14
    anke
    -0.13
    رة
    -0.13
    PURE
    -0.13
     &↵
    -0.13
    POSITIVE LOGITS
    onec
    0.15
    oire
    0.15
     rep
    0.14
    otland
    0.14
    icity
    0.14
    aniem
    0.13
    opia
    0.13
     Hava
    0.13
    ylon
    0.13
     Col
    0.13
    Act Density 0.016%

    No Known Activations