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

    Neuronpedia

    INDEX
    Explanations

    sequences indicating a duration of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to numerical measurements or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĶ°
    -0.76
    zsche
    -0.73
    enhagen
    -0.70
     Tuls
    -0.68
     tabs
    -0.68
    PsyNetMessage
    -0.67
    çīĪ
    -0.67
    ulkan
    -0.67
    rawdownloadcloneembedreportprint
    -0.67
     Mechdragon
    -0.66
    POSITIVE LOGITS
    ccording
    0.92
    minute
    0.89
    dozen
    0.89
    century
    0.82
    pillar
    0.80
    Lago
    0.80
    dollar
    0.77
    compl
    0.77
    cess
    0.77
    degree
    0.76
    Act Density 0.027%

    No Known Activations