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

    Neuronpedia

    INDEX
    Explanations

    words expressing uncertainty or anxiety about situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .habbo
    -0.18
    ÑĢик
    -0.16
    Ãĵ
    -0.15
    ιαÏĤ
    -0.15
     spel
    -0.15
     unto
    -0.15
    èĩ¨
    -0.14
    mer
    -0.14
     Americ
    -0.14
    oci
    -0.13
    POSITIVE LOGITS
     bahwa
    0.25
     rằng
    0.24
     ÏĮÏĦι
    0.21
     that
    0.21
     بأÙĨ
    0.17
    tings
    0.16
    that
    0.16
     дека
    0.15
    ัà¸Ļว
    0.15
     ÑĩÑĤо
    0.14
    Act Density 0.114%

    No Known Activations