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

    Neuronpedia

    INDEX
    Explanations

    the word "hi" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ala
    -0.15
    allet
    -0.15
    _SUITE
    -0.15
    auga
    -0.15
    atori
    -0.15
    ede
    -0.15
    vis
    -0.14
    sav
    -0.14
    mon
    -0.14
    ains
    -0.14
    POSITIVE LOGITS
    ÑĮко
    0.19
    ÃŃculo
    0.17
    _pri
    0.16
    stery
    0.15
    STALL
    0.14
    FRING
    0.14
    ucz
    0.14
    SError
    0.14
    λι
    0.14
    iyat
    0.14
    Act Density 0.015%

    No Known Activations