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

    Neuronpedia

    INDEX
    Explanations

    references to authorship and the act of writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illusion
    -0.71
    apon
    -0.70
    grounds
    -0.65
    asia
    -0.63
    ele
    -0.63
    eal
    -0.62
    EMS
    -0.61
    RS
    -0.60
    eno
    -0.59
     pneum
    -0.59
    POSITIVE LOGITS
     memos
    0.83
    vironment
    0.82
     letters
    0.78
    smanship
    0.77
     penned
    0.77
     textbooks
    0.76
     Letters
    0.76
     LET
    0.76
     papers
    0.76
    lishing
    0.75
    Act Density 0.028%

    No Known Activations