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

    Neuronpedia

    INDEX
    Explanations

    references to marriage and canonical practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erule
    -0.16
    ippy
    -0.14
    اص
    -0.14
    theid
    -0.14
    orget
    -0.14
    롱
    -0.14
    bib
    -0.13
    zung
    -0.13
    undler
    -0.13
     Dün
    -0.13
    POSITIVE LOGITS
     confession
    0.34
     pen
    0.34
     Conf
    0.33
     abs
    0.33
     conf
    0.29
     confess
    0.28
     Pen
    0.27
     confessed
    0.26
     Abs
    0.25
     Sac
    0.25
    Act Density 0.058%

    No Known Activations