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

    Neuronpedia

    INDEX
    Explanations

    statements emphasizing absolute certainty or lack of doubt

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize certainty or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritz
    -0.80
    ku
    -0.77
    por
    -0.76
    lines
    -0.75
    bern
    -0.74
    eds
    -0.74
    iv
    -0.73
    yi
    -0.73
    eg
    -0.73
    ahime
    -0.72
    POSITIVE LOGITS
    soever
    1.30
    THING
    1.13
     whatsoever
    1.10
     else
    1.05
     remotely
    0.90
    wcsstore
    0.87
     except
    0.87
     imaginable
    0.86
     conceivable
    0.85
    lihood
    0.83
    Act Density 0.007%

    No Known Activations