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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elda
    -0.17
    atel
    -0.17
    seau
    -0.15
    utomation
    -0.15
    aida
    -0.15
    alat
    -0.14
    rek
    -0.14
    beth
    -0.14
    plete
    -0.14
    ques
    -0.13
    POSITIVE LOGITS
    /***/
    0.16
    ↵↵
    0.15
    .toolbox
    0.15
    eus
    0.14
    914
    0.13
    .RowCount
    0.13
    ivec
    0.13
    æ¯Ľ
    0.13
    akra
    0.13
    @student
    0.13
    Act Density 0.101%

    No Known Activations