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

    Neuronpedia

    INDEX
    Explanations

    terms related to alcohol consumption and psychological states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fjspx
    -0.93
    lgari
    -0.90
    verwijspagina
    -0.89
    :✨
    -0.89
     oprot
    -0.84
    RegressionTest
    -0.84
    脚注の使い方
    -0.83
     kasarigan
    -0.82
     كومونز
    -0.82
     تضيفلها
    -0.81
    POSITIVE LOGITS
     also
    0.63
    -
    0.54
     
    0.51
     for
    0.51
    /
    0.50
     so
    0.48
     is
    0.48
     /
    0.48
     &
    0.47
     at
    0.47
    Act Density 0.898%

    No Known Activations