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

    Neuronpedia

    INDEX
    Explanations

    quotations and references

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly single and double quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ļ½
    -0.78
    ¾
    -0.71
    ²¾
    -0.69
    ¸
    -0.66
    psc
    -0.65
    İĭ
    -0.64
    cil
    -0.64
    tein
    -0.64
    ²
    -0.62
    acements
    -0.62
    POSITIVE LOGITS
    /"
    0.85
     AAP
    0.75
     ([
    0.71
     justifies
    0.65
     âĨij
    0.64
     âĨĴ
    0.62
     referring
    0.62
     advised
    0.62
     (*
    0.61
    âĹ¼
    0.61
    Act Density 0.080%

    No Known Activations