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

    Neuronpedia

    INDEX
    Explanations

    discussions of failure and mistakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.83
     estekak
    -0.81
    IntoConstraints
    -0.81
     ligiloj
    -0.79
    Παραπομπές
    -0.75
    Geplaatst
    -0.72
    GOTREF
    -0.72
    tvguidetime
    -0.72
     poveznice
    -0.69
    __':
    -0.68
    POSITIVE LOGITS
     big
    1.26
    big
    1.10
     BIG
    1.10
    BIG
    1.04
     badly
    0.91
     huge
    0.86
    Big
    0.85
     miserably
    0.85
     terribly
    0.84
     spectacular
    0.83
    Act Density 0.213%

    No Known Activations