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

    Neuronpedia

    INDEX
    Explanations

    numerical values and addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uce
    -0.17
    uchos
    -0.15
    one
    -0.15
    jamin
    -0.15
    zero
    -0.14
    ást
    -0.14
    pte
    -0.14
    body
    -0.14
     reduction
    -0.13
     otherwise
    -0.13
    POSITIVE LOGITS
    alsex
    0.17
    uitka
    0.16
    ediator
    0.16
    ModelError
    0.15
    Ping
    0.15
    ersistent
    0.15
     ping
    0.15
    _accessible
    0.15
    iaux
    0.15
    imson
    0.15
    Act Density 0.144%

    No Known Activations