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

    Neuronpedia

    INDEX
    Explanations

    expressions involving the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    as
    -0.53
    </em>
    -0.52
    AS
    -0.51
    ertz
    -0.49
    니다
    -0.47
    ome
    -0.43
    mod
    -0.43
    CC
    -0.42
    Optimized
    -0.42
    dası
    -0.42
    POSITIVE LOGITS
    хьтан
    0.89
     BorderRadius
    0.88
     HasFactory
    0.85
    énario
    0.84
    ſelf
    0.79
     समीक्षक
    0.78
    UpInside
    0.77
     poffe
    0.75
    ſelves
    0.75
    GOTREF
    0.74
    Act Density 0.368%

    No Known Activations