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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns and proper adjectives, likely related to places or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĵ
    -0.16
    ¢
    -0.15
    iband
    -0.14
    285
    -0.14
    fty
    -0.14
    hood
    -0.14
    ouse
    -0.14
    Assoc
    -0.14
     Chatt
    -0.13
    xt
    -0.13
    POSITIVE LOGITS
    ars
    0.19
     dep
    0.17
     imm
    0.16
    akat
    0.16
    metic
    0.15
    ñana
    0.15
    lems
    0.15
    аÑĢа
    0.15
    rna
    0.14
    rahim
    0.14
    Act Density 0.052%

    No Known Activations