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

    Neuronpedia

    INDEX
    Explanations

    specific unicode characters or character combinations

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.71
    chrom
    -0.68
    alien
    -0.68
     readiness
    -0.66
     chang
    -0.62
     apes
    -0.61
     Blacks
    -0.60
     partnerships
    -0.60
     Bounty
    -0.60
     magnitude
    -0.60
    POSITIVE LOGITS
    Ľ
    1.35
    ª
    0.92
    ł
    0.89
    ¸
    0.89
    ¾
    0.88
    ׾
    0.88
    Ùħ
    0.85
    ľ
    0.85
    姫
    0.84
    Ùĩ
    0.84
    Act Density 0.005%

    No Known Activations