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

    Neuronpedia

    INDEX
    Explanations

    phrases that incite action or excitement

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory or emphatic expressions often related to reactions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chin
    -0.72
     Cyr
    -0.72
     Aram
    -0.68
     Kaw
    -0.67
     Nass
    -0.66
     Chaff
    -0.66
     Chapman
    -0.65
    ©¶æ
    -0.65
     Shap
    -0.65
     Beir
    -0.64
    POSITIVE LOGITS
    !:
    1.41
    !'
    1.41
    !.
    1.36
    !,
    1.36
    !
    1.34
    !'"
    1.20
    !".
    1.14
    !"
    1.13
    !",
    1.12
    !]
    1.10
    Act Density 0.201%

    No Known Activations