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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or titles, particularly those in uppercase

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "THE" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fitting
    -0.72
    cd
    -0.71
    java
    -0.71
    uid
    -0.70
    let
    -0.69
    hm
    -0.68
    iod
    -0.67
    fired
    -0.67
    ander
    -0.66
    perties
    -0.66
    POSITIVE LOGITS
    ORY
    1.15
     LAST
    1.15
     FORM
    1.10
     IMAGES
    1.09
     STORY
    1.05
    ATER
    1.05
    IVERS
    1.03
    ISM
    1.03
     WEEK
    1.02
     DARK
    1.02
    Act Density 0.019%

    No Known Activations