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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific concept or action stated in the sentence, often involving a specific verb of action or identification

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a singular, central desire or goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.68
    untled
    -0.67
    Interstitial
    -0.61
    hovah
    -0.59
    azel
    -0.57
    achus
    -0.57
    ardy
    -0.57
    emort
    -0.57
    loo
    -0.56
    pite
    -0.54
    POSITIVE LOGITS
    :
    1.49
    %:
    1.32
    :-
    1.27
    *:
    1.23
     viz
    1.22
    :(
    1.21
    ):
    1.19
    ]:
    1.13
    :[
    1.12
    :"
    1.11
    Act Density 0.665%

    No Known Activations