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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions, inclusions, or specifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating exceptions or inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨ
    -0.62
     Klu
    -0.56
    urion
    -0.55
    pload
    -0.53
    ription
    -0.52
     Tray
    -0.52
    ãĥ¼ãĥĨãĤ£
    -0.51
     tyr
    -0.51
     Peach
    -0.50
     Citiz
    -0.50
    POSITIVE LOGITS
    .
    0.95
    !
    0.88
    ;
    0.85
    .[
    0.85
    ãĢĤ
    0.84
     :)
    0.83
     ;)
    0.83
    .,
    0.82
    —
    0.79
     ðŁĺ
    0.79
    Act Density 0.344%

    No Known Activations