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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "pub" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pub" and its variations, indicating a focus on publishing entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Spears
    -0.88
     Isles
    -0.76
     Esper
    -0.75
     Cognitive
    -0.70
     ANGEL
    -0.69
    IRD
    -0.69
     Elves
    -0.67
     Ellis
    -0.64
     Ducks
    -0.63
     Bots
    -0.63
    POSITIVE LOGITS
    lisher
    1.82
    lishing
    1.75
    pub
    1.48
    escent
    1.26
    lish
    1.26
    lishes
    1.25
    Pub
    1.13
    lique
    1.03
    lished
    0.98
    rophe
    0.92
    Act Density 0.007%

    No Known Activations