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

    Neuronpedia

    INDEX
    Explanations

    informal conversational phrases and expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     which
    -0.17
    igli
    -0.15
     WOW
    -0.14
    бо
    -0.14
    DidLoad
    -0.14
     whose
    -0.13
    ewan
    -0.13
    isini
    -0.13
    IALOG
    -0.13
     or
    -0.13
    POSITIVE LOGITS
     there
    0.17
     thems
    0.16
    they
    0.16
    ürn
    0.15
    we
    0.15
     they
    0.15
    tep
    0.15
    _this
    0.14
    there
    0.14
     we
    0.14
    Act Density 0.178%

    No Known Activations