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

    Neuronpedia

    INDEX
    Explanations

    the word "all."

    oai_token-act-pair · gpt-3.5-turbo

    instances of uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    visor
    -0.74
    ortment
    -0.69
    Discussion
    -0.69
    atari
    -0.66
    itton
    -0.65
    iang
    -0.65
    tnc
    -0.64
    john
    -0.63
    assic
    -0.61
    maximum
    -0.61
    POSITIVE LOGITS
     anymore
    1.77
     nor
    1.48
     whatsoever
    1.20
     anything
    1.20
     necessarily
    1.18
     anywhere
    1.14
     slightest
    1.08
     any
    1.07
     anybody
    1.03
     anyone
    0.95
    Act Density 1.795%

    No Known Activations