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

    Neuronpedia

    INDEX
    Explanations

    references to actions involving division or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xFFFFFF
    -0.16
    ILLA
    -0.15
    ÛĮÚ©ÛĮ
    -0.15
    acock
    -0.15
    Ïģοι
    -0.14
    alles
    -0.14
    à¹īว
    -0.14
    abeth
    -0.14
    ffi
    -0.14
    eph
    -0.14
    POSITIVE LOGITS
     hal
    0.30
     halves
    0.29
     Hal
    0.27
    -half
    0.26
    Hal
    0.24
    hal
    0.24
     half
    0.24
     Half
    0.24
     yarı
    0.23
     Äijôi
    0.23
    Act Density 0.039%

    No Known Activations