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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quantity or extent

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙIJ
    -0.83
    Ô
    -0.70
    chwitz
    -0.68
    ¯¯
    -0.68
    resy
    -0.67
    Policy
    -0.66
    IER
    -0.63
    wark
    -0.63
    iland
    -0.62
    ertodd
    -0.61
    POSITIVE LOGITS
     possibilities
    0.76
     digits
    0.71
     acron
    0.69
     bullets
    0.67
     contradictions
    0.66
    asses
    0.64
    ties
    0.64
     elements
    0.61
     beasts
    0.60
     totality
    0.60
    Act Density 0.179%

    No Known Activations