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

    Neuronpedia

    INDEX
    Explanations

    pronouns and words expressing measurement or conditions of necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ladu
    -0.18
    /MIT
    -0.16
    ROKE
    -0.16
    bef
    -0.16
    earn
    -0.15
    stell
    -0.15
    bery
    -0.15
    สว
    -0.15
    quire
    -0.15
    isson
    -0.14
    POSITIVE LOGITS
    ÏģÏĩ
    0.16
     Blasio
    0.15
    poly
    0.15
     Miracle
    0.15
    ala
    0.14
    rens
    0.14
    _PG
    0.14
    516
    0.14
     prime
    0.14
     blame
    0.14
    Act Density 0.006%

    No Known Activations