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

    Neuronpedia

    INDEX
    Explanations

    negation in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.08
    4:0.09
    5:0.09
    6:0.08
    7:0.09
    8:0.08
    9:0.07
    10:0.07
    11:0.07
    Negative Logits
     Corp
    -1.78
     Corporation
    -1.77
     Divinity
    -1.73
    etics
    -1.72
     Associates
    -1.69
     Enterprises
    -1.68
     Industries
    -1.67
     Leilan
    -1.61
     Tribunal
    -1.58
    utic
    -1.58
    POSITIVE LOGITS
     teasp
    1.99
    akespe
    1.86
     typo
    1.78
    wcs
    1.78
    vable
    1.78
     apr
    1.67
    risome
    1.62
     tast
    1.62
     culmin
    1.60
    00200000
    1.60
    Act Density 0.000%

    No Known Activations