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

    Neuronpedia

    INDEX
    Explanations

    names and phrases related to people or specific entities, potentially historical figures or organizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving brands or cultural references, particularly in the context of entertainment or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.87
    rawdownloadcloneembedreportprint
    -0.82
    idious
    -0.81
    ysis
    -0.77
    Äĩ
    -0.73
    iewicz
    -0.71
    nels
    -0.71
    tty
    -0.69
    idia
    -0.68
    dq
    -0.68
    POSITIVE LOGITS
    ãĥ¼ãĥĨ
    0.61
    Arcade
    0.59
    ãģŁ
    0.59
     riches
    0.57
    Spring
    0.56
    enced
    0.55
     rain
    0.55
     pound
    0.53
     shortest
    0.53
     heaviest
    0.53
    Act Density 0.348%

    No Known Activations