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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce attribution or sources of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertools
    -0.16
    Carthy
    -0.15
    raison
    -0.15
    ÚĨÛĮ
    -0.15
    xiety
    -0.15
    ertation
    -0.14
    sonian
    -0.14
     enthusi
    -0.14
    ëĥIJ
    -0.14
    /*č↵
    -0.14
    POSITIVE LOGITS
    e
    0.24
    s
    0.22
     to
    0.22
    er
    0.19
    eon
    0.17
    ly
    0.17
    sing
    0.17
    Ùĩ
    0.16
    ·
    0.15
    ÑģÑĮ
    0.15
    Act Density 0.003%

    No Known Activations