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

    Neuronpedia

    INDEX
    Explanations

    data or measurements related to various subjects, such as rankings, chemical composition, mood, and habits

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to measurements and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clusive
    -0.73
    cott
    -0.69
    ibus
    -0.68
    ulo
    -0.66
    pired
    -0.66
    fox
    -0.65
    lyn
    -0.65
    nov
    -0.64
    isha
    -0.64
    thouse
    -0.63
    POSITIVE LOGITS
     suscept
    0.83
     preferences
    0.80
     differed
    0.80
     attitudes
    0.80
     probabilities
    0.79
     tendencies
    0.78
     stru
    0.75
     differently
    0.75
     habits
    0.75
     disposition
    0.74
    Act Density 0.760%

    No Known Activations