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

    Neuronpedia

    INDEX
    Explanations

    references to monetary values or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erval
    -0.19
    awl
    -0.17
    çıł
    -0.16
    awi
    -0.15
    uet
    -0.15
    ally
    -0.14
     ÑģÑĤÑĢ
    -0.14
    ariat
    -0.14
    omb
    -0.14
    arget
    -0.14
    POSITIVE LOGITS
    umps
    0.17
    raq
    0.16
    alars
    0.15
    rav
    0.14
    -Language
    0.14
    волÑı
    0.13
    Ñĥб
    0.13
    rael
    0.13
    isser
    0.13
    blem
    0.13
    Act Density 0.119%

    No Known Activations