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

    Neuronpedia

    INDEX
    Explanations

    references to security measures and the evaluation of risks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alus
    -0.16
     Schultz
    -0.15
     Saud
    -0.15
    arkin
    -0.14
    lesc
    -0.14
     Outs
    -0.13
    ÄĻk
    -0.13
    ael
    -0.13
    ena
    -0.13
    uto
    -0.13
    POSITIVE LOGITS
     whose
    0.18
     or
    0.17
     nÃło
    0.16
    Tokens
    0.15
    idar
    0.15
    mamak
    0.15
    FormatException
    0.14
     such
    0.14
    whose
    0.14
    aldi
    0.14
    Act Density 0.320%

    No Known Activations