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

    Neuronpedia

    INDEX
    Explanations

    mention of diacritic marks in text

    oai_token-act-pair · gpt-3.5-turbo

    the character "ĵ" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enburg
    -0.75
    iewicz
    -0.71
    ouched
    -0.69
     Stras
    -0.67
    stadt
    -0.65
    umbledore
    -0.64
    ignment
    -0.64
    uminati
    -0.63
    ako
    -0.62
     Sims
    -0.61
    POSITIVE LOGITS
    âĸĵ
    1.07
    DIT
    0.92
    ¡
    0.90
    BLE
    0.89
    ĵ
    0.87
    iod
    0.84
    ×Ļ
    0.79
    ×ij
    0.77
    dd
    0.76
    į
    0.75
    Act Density 0.006%

    No Known Activations