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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _sdk
    -0.15
     (č↵
    -0.14
    asaki
    -0.14
    /GL
    -0.14
    mani
    -0.14
    stad
    -0.14
    ruba
    -0.14
    inen
    -0.14
    âĢĮÙ¾
    -0.13
    paged
    -0.13
    POSITIVE LOGITS
     sure
    0.24
    friend
    0.20
    eing
    0.19
    oggler
    0.18
     exact
    0.18
     aware
    0.18
     rid
    0.17
    ijing
    0.17
     precise
    0.17
    asty
    0.16
    Act Density 0.091%

    No Known Activations