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

    Neuronpedia

    INDEX
    Explanations

    punctuations and specific grammatical structures that indicate key information in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zove
    -0.36
    startsWith
    -0.36
    irlo
    -0.34
     iliy
    -0.34
     Persian
    -0.34
    drop
    -0.34
     Crete
    -0.34
    IDOS
    -0.34
     boldly
    -0.34
     Arabic
    -0.34
    POSITIVE LOGITS
    GEBURTSDATUM
    0.92
     But
    0.71
    But
    0.67
    LookAnd
    0.61
     but
    0.61
     betweenstory
    0.60
    but
    0.59
    RUnlock
    0.58
     незавершена
    0.57
    erdings
    0.57
    Act Density 0.214%

    No Known Activations