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

    Neuronpedia

    INDEX
    Explanations

    words related to strong emotions or actions, like anger, enthusiasm, or violence

    oai_token-act-pair · gpt-3.5-turbo

    words related to Australian context and expressions of emotional intensity such as reprimanding or criticizing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.88
    eworks
    -0.84
    ality
    -0.79
    ffic
    -0.79
    ãĥĺ
    -0.79
    enhagen
    -0.77
    DragonMagazine
    -0.77
    govtrack
    -0.75
    ouri
    -0.74
    utical
    -0.74
    POSITIVE LOGITS
     stern
    0.70
    keley
    0.68
     Aqu
    0.67
    thal
    0.66
     Camb
    0.66
     solitary
    0.65
     Harbor
    0.64
     XVI
    0.64
     ber
    0.64
     Tud
    0.63
    Act Density 0.049%

    No Known Activations