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

    Neuronpedia

    INDEX
    Explanations

    propper nouns or specific entity mentions in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "AL" and variations of its capitalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sterling
    -0.75
    ãĥ¼ãĥĨãĤ£
    -0.65
    åĤ
    -0.63
     neutral
    -0.61
     Dai
    -0.61
     Generations
    -0.61
     Solitaire
    -0.60
     Tycoon
    -0.60
    NT
    -0.59
    ãģĭ
    -0.59
    POSITIVE LOGITS
    cohol
    1.38
    ibaba
    1.35
    uminum
    1.35
    phabet
    1.33
    buquerque
    1.26
    manac
    1.25
    bum
    1.24
    gebra
    1.24
    onso
    1.23
    chemy
    1.23
    Act Density 0.025%

    No Known Activations