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

    Neuronpedia

    INDEX
    Explanations

    lists of variables and their properties in coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zew
    -0.19
    rim
    -0.17
    ussen
    -0.15
    mund
    -0.15
    shaw
    -0.15
     Murphy
    -0.14
    ÌĤ
    -0.14
    опол
    -0.14
    oot
    -0.14
    ardi
    -0.14
    POSITIVE LOGITS
     boolean
    0.19
    boolean
    0.18
     int
    0.17
     bool
    0.17
     const
    0.15
    strings
    0.15
    .bool
    0.15
    entar
    0.14
    agnar
    0.14
    /her
    0.14
    Act Density 0.039%

    No Known Activations