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

    Neuronpedia

    INDEX
    Explanations

    phrases that are used to qualify a statement in a less precise or exact manner

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate an approximate or imprecise relationship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Org
    -0.76
     Enhancement
    -0.74
     Lovely
    -0.72
    zees
    -0.71
    iaries
    -0.70
    olphin
    -0.70
    yl
    -0.69
    */(
    -0.68
    igate
    -0.68
    inctions
    -0.66
    POSITIVE LOGITS
     loosely
    1.07
     veiled
    0.84
     exting
    0.79
    atory
    0.75
     affiliated
    0.74
     dispersed
    0.69
     vers
    0.67
    luster
    0.67
    interstitial
    0.67
    unct
    0.66
    Act Density 0.012%

    No Known Activations