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

    Neuronpedia

    INDEX
    Explanations

    terms related to benchmarking and quality assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ании
    -0.15
     Fabric
    -0.15
    ̣
    -0.15
    ys
    -0.15
    USE
    -0.14
     erg
    -0.14
    ël
    -0.13
     Oh
    -0.13
    encer
    -0.13
    elt
    -0.13
    POSITIVE LOGITS
    marks
    0.18
     Bair
    0.16
    iếu
    0.16
    ing
    0.15
    iyan
    0.15
    edor
    0.15
    ingham
    0.15
    θÎŃ
    0.14
    .rd
    0.14
    #
    0.14
    Act Density 0.008%

    No Known Activations