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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "nor" indicating negation or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McCart
    -0.16
    rchive
    -0.15
    enko
    -0.15
    ing
    -0.15
    urs
    -0.15
    agle
    -0.14
    392
    -0.14
    itious
    -0.14
    sch
    -0.14
     ric
    -0.14
    POSITIVE LOGITS
     tamp
    0.17
    theless
    0.17
     shalt
    0.16
    deen
    0.16
    lify
    0.16
    licht
    0.15
    ãĤīãģĦ
    0.15
    thern
    0.15
    лади
    0.15
    thing
    0.15
    Act Density 0.022%

    No Known Activations