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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mistakes and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    'gc
    -0.17
    /Dk
    -0.15
    .Networking
    -0.14
    ÎķÎļ
    -0.14
    ków
    -0.14
    ÑĢÑĥк
    -0.14
    VisualStyle
    -0.14
    Ïģαβ
    -0.14
    oids
    -0.13
    ìłĦìĹIJ
    -0.13
    POSITIVE LOGITS
    Ìģ
    0.17
     coll
    0.15
    0.15
     ë²Ī째
    0.15
    æ½
    0.14
    çij
    0.14
     Zd
    0.14
    alker
    0.13
    jumbotron
    0.13
     slim
    0.13
    Act Density 0.537%

    No Known Activations