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

    Neuronpedia

    INDEX
    Explanations

    common conjunctions and pronouns significant for connecting ideas in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astle
    -0.17
    érc
    -0.16
    tridges
    -0.16
    facet
    -0.15
    IFO
    -0.15
     Bust
    -0.15
     Pig
    -0.15
    931
    -0.15
    abe
    -0.15
    alar
    -0.15
    POSITIVE LOGITS
    coli
    0.15
    incible
    0.15
     wall
    0.14
    isay
    0.14
    teri
    0.14
     twice
    0.14
    XD
    0.14
    .addButton
    0.14
    usable
    0.13
    éĢ¸
    0.13
    Act Density 0.003%

    No Known Activations