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

    Neuronpedia

    INDEX
    Explanations

    specific pronouns preceding descriptive words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ward
    -0.75
    Supported
    -0.74
    lihood
    -0.73
    ESA
    -0.72
     thereby
    -0.72
    kell
    -0.70
    linked
    -0.70
    nesty
    -0.69
     amid
    -0.69
     according
    -0.69
    POSITIVE LOGITS
     coolest
    1.27
     slightest
    1.25
     guy
    1.15
     whole
    1.15
     damn
    1.13
     goddamn
    1.12
     same
    1.08
     fuckin
    1.07
     fucking
    1.05
     crap
    1.04
    Act Density 0.846%

    No Known Activations