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

    Neuronpedia

    INDEX
    Explanations

    questions and phrases related to methods or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    him
    -0.17
    irs
    -0.17
     eux
    -0.17
    them
    -0.16
     THEM
    -0.15
    Them
    -0.15
     lui
    -0.15
     herself
    -0.14
    ãĤĮãģªãģĦ
    -0.14
    _known
    -0.14
    POSITIVE LOGITS
    /if
    0.35
     much
    0.33
     exactly
    0.33
    soever
    0.32
     else
    0.31
     they
    0.30
     we
    0.29
     best
    0.28
     far
    0.27
    beit
    0.26
    Act Density 0.098%

    No Known Activations