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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a strong contrast or transition in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     peixes
    -0.48
    ⓧ
    -0.44
    ljen
    -0.44
    wnętr
    -0.42
    logrus
    -0.41
    Jeografia
    -0.41
     fizer
    -0.41
     enquiry
    -0.41
    ελ
    -0.40
     soeur
    -0.40
    POSITIVE LOGITS
     —
    1.38
     —,
    0.98
    .—
    0.93
    —
    0.91
    ,—
    0.88
    —.
    0.83
    ?—
    0.83
    ———
    0.82
    ————
    0.82
    )—
    0.81
    Act Density 0.385%

    No Known Activations