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

    Neuronpedia

    INDEX
    Explanations

    text related to technical specifications or product details

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols or characters mixed with certain phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vironment
    -0.70
    yright
    -0.63
    ĸļ
    -0.62
    erness
    -0.62
    awa
    -0.60
    theless
    -0.60
    ã
    -0.60
    CHR
    -0.59
    NPR
    -0.58
    Termin
    -0.57
    POSITIVE LOGITS
     Genius
    0.73
     Corruption
    0.70
    sic
    0.69
     Equip
    0.67
    ashtra
    0.66
     Beaut
    0.65
     Regist
    0.62
    aternity
    0.62
     Niet
    0.61
    aneous
    0.61
    Act Density 0.864%

    No Known Activations