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

    Neuronpedia

    INDEX
    Explanations

    instances of references to multiple authors in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FUL
    -0.65
    ensical
    -0.65
    é¾įå¥ij士
    -0.60
    atever
    -0.57
     Deliver
    -0.56
     headsets
    -0.56
    Experience
    -0.55
    ATTLE
    -0.55
    ldon
    -0.54
    ardless
    -0.54
    POSITIVE LOGITS
     al
    1.37
     seq
    1.25
    rics
    0.88
    seq
    0.83
    ching
    0.81
    ree
    0.80
    ches
    0.80
    su
    0.79
     Associates
    0.75
    rand
    0.75
    Act Density 0.012%

    No Known Activations