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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to playing time and incarceration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.93
    joining
    -0.80
    inosaur
    -0.79
    selage
    -0.79
    riad
    -0.74
    dyl
    -0.73
    uthor
    -0.73
    urat
    -0.73
    hid
    -0.70
    inav
    -0.70
    POSITIVE LOGITS
    frames
    1.01
    outs
    0.85
     expectancy
    0.79
     continuum
    0.79
    zone
    0.76
     indoors
    0.73
     periods
    0.73
    aneously
    0.69
     noodles
    0.68
     Corpus
    0.67
    Act Density 0.054%

    No Known Activations