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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contextual significance in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oth
    -0.15
    however
    -0.14
    IGHL
    -0.14
    ife
    -0.14
    Specifier
    -0.13
    rag
    -0.13
     Mig
    -0.13
    unci
    -0.13
    iaux
    -0.13
    ا
    -0.13
    POSITIVE LOGITS
    Ïģαν
    0.19
     hence
    0.16
     srov
    0.15
    terra
    0.15
    -uppercase
    0.15
    /groups
    0.14
    oret
    0.13
    roman
    0.13
    amil
    0.13
    .Usage
    0.13
    Act Density 0.116%

    No Known Activations