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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _sdk
    -0.15
     (č↵
    -0.14
    udu
    -0.14
    (animated
    -0.14
    hdl
    -0.14
    irie
    -0.14
    اÙĦÙĩ
    -0.13
    stad
    -0.13
    /GL
    -0.13
    paged
    -0.13
    POSITIVE LOGITS
     sure
    0.27
     aware
    0.21
    sure
    0.20
     precise
    0.19
    friend
    0.19
     exact
    0.19
     used
    0.19
     Sure
    0.18
    eing
    0.17
    eline
    0.17
    Act Density 0.062%

    No Known Activations