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

    Neuronpedia

    INDEX
    Explanations

    adjectives or phrases related to strength, importance, or uniqueness

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that denote strong qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.62
     CoC
    -0.59
    Quote
    -0.57
    NZ
    -0.56
    othy
    -0.52
    ixels
    -0.52
    hemy
    -0.52
    EEK
    -0.51
    chan
    -0.51
     Sandwich
    -0.50
    POSITIVE LOGITS
     enough
    1.25
    amount
    1.03
    enough
    1.02
     thereto
    0.93
    itaire
    0.92
     to
    0.78
    iates
    0.74
    aneously
    0.73
    ties
    0.73
     Enough
    0.72
    Act Density 0.194%

    No Known Activations