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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing negation or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĥ
    -0.80
    interstitial
    -0.75
    éĹĺ
    -0.71
    å¥
    -0.71
    itech
    -0.70
    lined
    -0.68
    è»
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
     Steps
    -0.64
     arsen
    -0.63
    POSITIVE LOGITS
     necessarily
    1.60
    icably
    1.21
    withstanding
    1.12
     exactly
    1.08
    icable
    1.06
     yet
    0.96
    orious
    0.92
     always
    0.91
    necess
    0.90
     entirely
    0.87
    Act Density 0.220%

    No Known Activations