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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "speak" or its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wide
    -0.15
     ra
    -0.15
     fact
    -0.15
    ecycle
    -0.15
     Berger
    -0.14
    gart
    -0.14
    ft
    -0.14
     Gould
    -0.14
    wide
    -0.14
    igan
    -0.13
    POSITIVE LOGITS
     mixins
    0.15
    gın
    0.15
    =-=-=-=-=-=-=-=-
    0.14
    θι
    0.14
    umas
    0.14
     atol
    0.14
     mixin
    0.14
    YPRE
    0.14
    _mB
    0.13
    ync
    0.13
    Act Density 0.021%

    No Known Activations