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

    Neuronpedia

    INDEX
    Explanations

    Arabic characters and words related to preferences and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.74
    UnusedPrivate
    -0.74
     Eſ
    -0.73
     houſe
    -0.73
     purpoſe
    -0.72
    enderror
    -0.72
     ſen
    -0.70
    ########.
    -0.69
     Inſ
    -0.69
    ValueStyle
    -0.69
    POSITIVE LOGITS
     se
    0.71
     έχει
    0.53
     نفت
    0.47
     Se
    0.46
    يع
    0.45
     ي
    0.44
     تكبرها
    0.43
    fromCharCode
    0.43
     נ
    0.43
     يت
    0.42
    Act Density 0.002%

    No Known Activations