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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a small amount or quantity of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating small quantities or limited numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqor
    -0.78
     Skies
    -0.75
    ais
    -0.74
    rench
    -0.69
     GOODMAN
    -0.67
    cellent
    -0.66
    renches
    -0.66
    ukong
    -0.66
    nance
    -0.65
    1920
    -0.64
    POSITIVE LOGITS
     (<
    1.11
     trickle
    0.81
     subset
    0.73
    elist
    0.67
     newsp
    0.66
     tolerated
    0.65
     exceptions
    0.64
     outl
    0.64
    */(
    0.64
     fraction
    0.62
    Act Density 0.164%

    No Known Activations