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

    Neuronpedia

    INDEX
    Explanations

    interesting, strange, or unusual occurrences or facts

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe novelty or curiosity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hops
    -0.99
    hers
    -0.87
    ULTS
    -0.83
    ernels
    -0.82
    ecause
    -0.79
    iants
    -0.79
     Tanks
    -0.78
    Ĥİ
    -0.78
    lees
    -0.78
    stones
    -0.78
    POSITIVE LOGITS
     twist
    1.14
     distinction
    1.09
     anecdote
    1.04
     tale
    1.02
     combination
    1.01
     example
    1.01
     caveat
    1.00
     array
    0.99
     statistic
    0.99
     glimpse
    0.99
    Act Density 0.225%

    No Known Activations