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

    Neuronpedia

    INDEX
    Explanations

    the frequency of the word "over" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yat
    -0.16
    528
    -0.16
    &↵
    -0.15
    OT
    -0.15
    ursday
    -0.14
    720
    -0.14
    obile
    -0.13
    çĵ¶
    -0.13
    bib
    -0.13
    pes
    -0.13
    POSITIVE LOGITS
    .Fat
    0.17
    heard
    0.17
    ãĤªãĥª
    0.15
    beck
    0.15
    ombine
    0.15
    tri
    0.15
    eview
    0.15
    unning
    0.14
    iginal
    0.14
    eny
    0.14
    Act Density 0.086%

    No Known Activations