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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a rate or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yard
    -0.21
    tober
    -0.15
    ury
    -0.15
    naire
    -0.15
    ebi
    -0.14
    stag
    -0.14
    plain
    -0.14
    erview
    -0.14
    zilla
    -0.14
    .microsoft
    -0.14
    POSITIVE LOGITS
     annum
    0.26
    iphery
    0.24
     capita
    0.23
    ipher
    0.20
    cents
    0.20
    missive
    0.19
    pend
    0.18
    hap
    0.17
    quisites
    0.17
     usual
    0.17
    Act Density 0.021%

    No Known Activations