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

    Neuronpedia

    INDEX
    Explanations

    percentage values

    oai_token-act-pair · gpt-3.5-turbo

    percentage values and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.67
     skelet
    -0.63
     Constantin
    -0.61
     patriarch
    -0.61
     lun
    -0.60
     tyrann
    -0.60
    shit
    -0.57
     pals
    -0.57
    iris
    -0.56
     nour
    -0.56
    POSITIVE LOGITS
    ooters
    0.94
    iversary
    0.86
    iewicz
    0.81
    ordable
    0.77
    eele
    0.72
    ugg
    0.71
    okers
    0.71
    ihilation
    0.71
    icans
    0.68
    _>
    0.68
    Act Density 0.051%

    No Known Activations