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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urus
    -0.17
    riad
    -0.15
    vla
    -0.15
    COPE
    -0.15
    wick
    -0.15
    ussen
    -0.15
    nid
    -0.15
    opard
    -0.14
     å¹
    -0.14
    ربÙĩ
    -0.14
    POSITIVE LOGITS
    iams
    0.18
    ooks
    0.17
    lain
    0.17
    imator
    0.15
    asts
    0.15
    l
    0.15
    piler
    0.15
    .ret
    0.14
    IJ
    0.14
     erw
    0.14
    Act Density 0.020%

    No Known Activations