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

    Neuronpedia

    INDEX
    Explanations

    phrases related to roles and responsibilities in a communal setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ycz
    -0.15
    uled
    -0.14
    orsch
    -0.14
    bons
    -0.14
    .nan
    -0.14
     Fah
    -0.14
    anes
    -0.13
     Praha
    -0.13
    ORIA
    -0.13
     stag
    -0.13
    POSITIVE LOGITS
    DialogContent
    0.15
    -inverse
    0.14
    conduct
    0.14
    /licenses
    0.14
     Blackburn
    0.14
     pearl
    0.14
    ati
    0.14
    alex
    0.13
    erif
    0.13
    競
    0.13
    Act Density 0.032%

    No Known Activations