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

    Neuronpedia

    INDEX
    Explanations

    instances of phrases introducing a source or reference

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "that" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rule
    -0.64
    GY
    -0.61
     dying
    -0.60
    natureconservancy
    -0.59
     downtime
    -0.58
    animate
    -0.57
     retiring
    -0.56
     Favorite
    -0.56
     expectation
    -0.56
    zero
    -0.55
    POSITIVE LOGITS
     summarizes
    1.38
     depicts
    1.36
     outlines
    1.30
     illustrates
    1.25
     contains
    1.23
     discusses
    1.23
     describes
    1.22
     summar
    1.19
     includes
    1.17
     summarize
    1.16
    Act Density 0.213%

    No Known Activations