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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms in language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¸Ī
    -0.14
    ashed
    -0.14
    bsub
    -0.14
    øy
    -0.14
    urch
    -0.14
    bu
    -0.14
     Kling
    -0.14
    Stub
    -0.14
     Tenn
    -0.14
    vens
    -0.13
    POSITIVE LOGITS
    _KP
    0.17
    isci
    0.16
    /wp
    0.15
     explan
    0.14
    IDI
    0.14
    सम
    0.14
    meer
    0.14
    )const
    0.14
    .Automation
    0.14
    ibi
    0.13
    Act Density 0.239%

    No Known Activations