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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "will" and its variations, indicating predictions or future intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illions
    -0.15
    atti
    -0.15
    arend
    -0.14
    иÑĢа
    -0.14
    elor
    -0.14
    opr
    -0.14
     понÑıÑĤÑĮ
    -0.14
    istas
    -0.14
    Çİ
    -0.14
    enido
    -0.13
    POSITIVE LOGITS
     be
    0.40
    iams
    0.32
    iam
    0.31
     likely
    0.27
    l
    0.27
    IAM
    0.25
    kommen
    0.23
    likely
    0.23
     not
    0.21
    ä¸įä¼ļ
    0.21
    Act Density 0.359%

    No Known Activations