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

    Neuronpedia

    INDEX
    Explanations

    words related to violence and intimidation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the possessive form of the word "Bills."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ļ½
    -0.70
    vg
    -0.66
    ī
    -0.65
    İĭ
    -0.64
     Ducks
    -0.62
     Izan
    -0.62
     Archangel
    -0.61
     -=
    -0.60
     Reduce
    -0.57
     ..............
    -0.57
    POSITIVE LOGITS
     own
    0.84
     fingerprints
    0.69
     birthplace
    0.69
    cause
    0.69
    ELF
    0.69
     penchant
    0.68
    Interstitial
    0.65
    Cause
    0.65
    Own
    0.64
     sake
    0.64
    Act Density 0.038%

    No Known Activations