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

    Neuronpedia

    INDEX
    Explanations

    foreign language characters or words

    oai_token-act-pair · gpt-3.5-turbo

    non-standard or special characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olicy
    -0.93
    arton
    -0.92
    hani
    -0.91
    leground
    -0.80
    etsk
    -0.76
    achy
    -0.75
    olf
    -0.75
    lycer
    -0.74
    iasco
    -0.74
    olit
    -0.74
    POSITIVE LOGITS
    ãĤ
    1.50
    ãĥĩ
    1.40
    ãģª
    1.37
    ãĥ«
    1.37
    ãĥ¬
    1.36
    ãĥ¼ãĥ³
    1.35
    ãģ
    1.34
    ãĤ½
    1.32
    ãĥ¼ãĥ
    1.32
    ãĥ©
    1.30
    Act Density 0.012%

    No Known Activations