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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific names mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the structure "the name of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ienne
    -0.73
     pse
    -0.71
    imeo
    -0.70
    iasm
    -0.69
    alysis
    -0.68
    iol
    -0.68
    ien
    -0.68
    igmatic
    -0.67
     deterior
    -0.66
    umerable
    -0.66
    POSITIVE LOGITS
     Uzbek
    0.78
     Hawaiian
    0.73
     Tup
    0.71
    thood
    0.70
     Hussein
    0.70
     Jesus
    0.67
     Hamm
    0.67
     Savior
    0.67
    ãĤ±
    0.66
     Father
    0.66
    Act Density 0.135%

    No Known Activations