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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "rhetoric" and related terms, indicating a focus on discourse and language used in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bies
    -0.15
    hap
    -0.15
     scoop
    -0.15
     tsl
    -0.14
    PLICIT
    -0.14
    crest
    -0.14
    íģ¼
    -0.14
    ª
    -0.14
    iverz
    -0.14
    ainen
    -0.14
    POSITIVE LOGITS
    orical
    0.17
    elves
    0.16
    idal
    0.15
    /stat
    0.15
    ÑĤÑĥ
    0.15
    mith
    0.15
    ical
    0.14
    odel
    0.14
    ../../../
    0.14
    ALLY
    0.14
    Act Density 0.006%

    No Known Activations