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

    Neuronpedia

    INDEX
    Explanations

    terms related to benchmarking and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    finger
    -0.15
    licer
    -0.14
    reau
    -0.14
    rå
    -0.14
    лÑĥж
    -0.14
    kili
    -0.13
    fur
    -0.13
    oard
    -0.13
    iliar
    -0.13
    edik
    -0.13
    POSITIVE LOGITS
    ing
    0.81
    ING
    0.44
    ings
    0.36
    ingt
    0.34
    ers
    0.34
    ation
    0.30
    ning
    0.29
    ingen
    0.27
    ÂŃing
    0.27
    ë§ģ
    0.27
    Act Density 0.511%

    No Known Activations