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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to equipment specifications

    oai_token-act-pair · gpt-3.5-turbo

    the character "ĸ" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arios
    -0.86
    olitan
    -0.82
     Gamb
    -0.78
    iewicz
    -0.73
     Lann
    -0.72
    raint
    -0.72
    raints
    -0.72
    iful
    -0.69
    inctions
    -0.68
     Afric
    -0.67
    POSITIVE LOGITS
    åĤ
    1.01
    nder
    0.93
    âĹ¼
    0.90
    ĸ
    0.90
    ¾
    0.90
    ï¸ı
    0.89
    çķ
    0.89
    gy
    0.86
    ħĭ
    0.86
    fter
    0.82
    Act Density 0.006%

    No Known Activations