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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of charting or being charted

    oai_token-act-pair · gpt-3.5-turbo

    past participles of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wond
    -0.77
    reach
    -0.73
     includ
    -0.73
    estamp
    -0.67
    axter
    -0.65
    fit
    -0.62
    sight
    -0.61
    anchester
    -0.61
    spe
    -0.61
     shack
    -0.60
    POSITIVE LOGITS
    berus
    0.85
    utical
    0.78
    uled
    0.75
    ornia
    0.75
    emption
    0.74
    ript
    0.72
    00200000
    0.71
    ultural
    0.71
    ragon
    0.70
    ridor
    0.69
    Act Density 0.018%

    No Known Activations