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

    Neuronpedia

    INDEX
    Explanations

    indications of additional information or elaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lug
    -0.17
    rum
    -0.16
    ãĥĨãĥ«
    -0.15
    à¥įयप
    -0.15
    uito
    -0.15
    ration
    -0.14
    ernen
    -0.14
    eln
    -0.14
    sel
    -0.14
     lug
    -0.14
    POSITIVE LOGITS
    ance
    0.25
    most
    0.24
    -than
    0.22
    ing
    0.21
     ado
    0.21
    er
    0.19
    MORE
    0.19
    -reaching
    0.18
    hin
    0.18
     than
    0.17
    Act Density 0.022%

    No Known Activations