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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    contractions with apostrophes (particularly "'s" and "'t").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.35
     мәкал
    -0.35
    PathParam
    -0.34
     Mercier
    -0.34
    Aholisi
    -0.33
    舺
    -0.33
     springfox
    -0.33
    ۣ
    -0.32
     nap
    -0.31
    ंदीखरीदारी
    -0.31
    POSITIVE LOGITS
    IntoConstraints
    0.52
     plufieurs
    0.51
     mijne
    0.47
     Christiane
    0.45
    InSection
    0.45
    certainty
    0.44
    Datuak
    0.44
    pulumi
    0.44
     zijne
    0.44
     certainty
    0.43
    Act Density 0.062%

    No Known Activations