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

    Neuronpedia

    INDEX
    Explanations

    expressions related to expectations or predictions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of expectation or assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jab
    -0.78
    rawdownloadcloneembedreportprint
    -0.70
    chin
    -0.69
    uesday
    -0.66
    ftime
    -0.64
    rio
    -0.63
    ifax
    -0.62
    wings
    -0.62
    fake
    -0.59
    eon
    -0.59
    POSITIVE LOGITS
     logically
    0.82
     Wouldn
    0.75
     would
    0.73
     prudent
    0.73
     logical
    0.71
     wouldn
    0.69
     someone
    0.69
    DragonMagazine
    0.68
     ideally
    0.66
     sensible
    0.64
    Act Density 0.285%

    No Known Activations