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

    Neuronpedia

    INDEX
    Explanations

    adjectives or phrases related to characteristics or qualities

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors that convey qualities or characteristics of objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.65
    atel
    -0.65
    avorite
    -0.64
    avery
    -0.64
    FORE
    -0.62
    essler
    -0.60
    irrel
    -0.58
     teasp
    -0.58
    anova
    -0.58
    none
    -0.56
    POSITIVE LOGITS
     than
    2.18
    than
    1.80
     Than
    1.64
    worldly
    0.89
    erous
    0.86
    istant
    0.70
     oriented
    0.69
     embodiments
    0.68
    lly
    0.67
     versions
    0.65
    Act Density 0.221%

    No Known Activations