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

    Neuronpedia

    INDEX
    Explanations

    phrases where something is looming over or hovering above

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "over" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illary
    -0.82
    ¯¯¯¯
    -0.65
    STAR
    -0.63
    onna
    -0.62
     Levine
    -0.61
     partName
    -0.61
    CONCLUS
    -0.60
    ãĥ¼ãĥĨ
    -0.60
    oko
    -0.59
    Ô
    -0.58
    POSITIVE LOGITS
    drive
    1.01
    hang
    0.97
    lord
    0.92
    loading
    0.91
    tones
    0.88
    reaching
    0.83
    mast
    0.82
    rule
    0.80
    hung
    0.80
    lay
    0.74
    Act Density 0.056%

    No Known Activations