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

    Neuronpedia

    INDEX
    Explanations

    specific Unicode characters

    oai_token-act-pair · gpt-3.5-turbo

    the character "Ä" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izable
    -0.82
    wcs
    -0.69
    stocks
    -0.66
    waves
    -0.65
    fell
    -0.64
     goodwill
    -0.63
     giveaways
    -0.62
    mort
    -0.62
     mutual
    -0.62
     Binary
    -0.61
    POSITIVE LOGITS
    ĥ
    1.38
    ħ
    1.38
    ¼
    1.35
    Ľ
    1.34
    Ķ
    1.34
    Ģ
    1.34
    ı
    1.34
    Į
    1.33
    İ
    1.31
    °
    1.30
    Act Density 0.004%

    No Known Activations