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

    Neuronpedia

    INDEX
    Explanations

    the word "will" indicating future actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stry
    -0.16
    elon
    -0.15
    oksen
    -0.14
    pcf
    -0.14
    eli
    -0.14
    elor
    -0.14
    ically
    -0.13
    emales
    -0.13
    ideo
    -0.13
    guard
    -0.13
    POSITIVE LOGITS
    iams
    0.25
    kommen
    0.21
    iam
    0.18
    l
    0.16
     be
    0.15
    IAM
    0.15
    iger
    0.14
    ÑĢоÑī
    0.14
    iston
    0.13
    fully
    0.13
    Act Density 0.286%

    No Known Activations