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

    Neuronpedia

    INDEX
    Explanations

    phrases related to systems or methods of doing things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baum
    -0.17
    lou
    -0.15
    clair
    -0.14
    unidad
    -0.14
    maal
    -0.14
    wig
    -0.14
    lemen
    -0.14
    pedia
    -0.14
    ipher
    -0.13
     runaway
    -0.13
    POSITIVE LOGITS
    fully
    0.18
    finding
    0.17
    dra
    0.16
    ward
    0.16
    etically
    0.16
    ook
    0.15
    ÅĽci
    0.15
    yyy
    0.15
    yyyy
    0.15
    arden
    0.14
    Act Density 0.104%

    No Known Activations