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

    Neuronpedia

    INDEX
    Explanations

    strong descriptive phrases or adjectives that convey excellence or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Famous
    -0.14
     McKay
    -0.14
     Guess
    -0.14
    ction
    -0.13
    istik
    -0.13
    ething
    -0.13
    วล
    -0.13
     Alias
    -0.13
    allest
    -0.13
     forall
    -0.13
    POSITIVE LOGITS
     treat
    0.30
     true
    0.29
     absolute
    0.26
     must
    0.24
     steal
    0.24
     definite
    0.24
     real
    0.23
     pleasure
    0.23
     winner
    0.23
    ces
    0.22
    Act Density 0.184%

    No Known Activations