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

    Neuronpedia

    INDEX
    Explanations

    words in a specific foreign language script

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'ı' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xus
    -0.85
    ftime
    -0.85
     surv
    -0.81
     desper
    -0.78
     traged
    -0.77
     compr
    -0.77
     confir
    -0.76
    icter
    -0.73
     hatched
    -0.73
     conduc
    -0.72
    POSITIVE LOGITS
    æµ
    0.93
    ãĤĮ
    0.89
    dash
    0.88
    cup
    0.85
    system
    0.82
    âĶģ
    0.81
    dan
    0.80
    ä¼
    0.77
    Cloud
    0.76
    åİ
    0.76
    Act Density 0.009%

    No Known Activations