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

    Neuronpedia

    INDEX
    Explanations

    numeric values, particularly large numbers and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÛĮÙĨÚ¯
    -0.15
    uman
    -0.15
    ear
    -0.14
    Ùij
    -0.14
    ée
    -0.14
    ota
    -0.14
    ipse
    -0.14
    fuse
    -0.14
    еÑħ
    -0.13
    IVER
    -0.13
    POSITIVE LOGITS
    ths
    0.21
    mAh
    0.17
    ed
    0.16
    ì§ľ
    0.16
    th
    0.16
    -plus
    0.16
    edir
    0.15
    indsight
    0.15
    liness
    0.15
    zie
    0.15
    Act Density 0.076%

    No Known Activations