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

    Neuronpedia

    INDEX
    Explanations

    Unnamed characters in formatted text

    oai_token-act-pair · gpt-3.5-turbo

    indicators of anticipation or upcoming events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     undermin
    -0.69
     neighb
    -0.68
     underest
    -0.67
     blinded
    -0.66
     disapprove
    -0.64
     biod
    -0.63
     dazz
    -0.61
     prosec
    -0.61
     contempl
    -0.61
     distances
    -0.61
    POSITIVE LOGITS
    ³³³³³³³³
    1.20
    ³³³³³³³³³³³³³³³³
    1.15
    ³³³³
    1.09
    Yesterday
    1.08
    Thankfully
    1.04
    Anyway
    1.01
    Fortunately
    1.01
    ³³³
    1.01
    Naturally
    0.99
    Luckily
    0.98
    Act Density 0.543%

    No Known Activations