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

    Neuronpedia

    INDEX
    Explanations

    key quantitative metrics and details regarding complexity, selection criteria, and product performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivol
    -0.15
    acher
    -0.13
    ipop
    -0.13
    äge
    -0.13
    elden
    -0.13
    nex
    -0.13
    isoner
    -0.13
    addon
    -0.13
    venge
    -0.13
    adden
    -0.13
    POSITIVE LOGITS
    orest
    0.14
     Oswald
    0.13
    rego
    0.13
     prim
    0.13
    SCRI
    0.13
    εÏĦ
    0.12
    .assertThat
    0.12
     Volk
    0.12
    /MPL
    0.12
    Ĭ
    0.12
    Act Density 0.152%

    No Known Activations