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

    Neuronpedia

    INDEX
    Explanations

    references to bullets or bullet points in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hire
    -0.16
    ibar
    -0.15
    .ToDateTime
    -0.15
    íĴĪ
    -0.15
    kah
    -0.15
    amel
    -0.15
    ilon
    -0.15
    onet
    -0.15
    amins
    -0.14
    exampleInput
    -0.14
    POSITIVE LOGITS
    proof
    0.28
    -proof
    0.19
    -shaped
    0.17
    aneous
    0.17
     trains
    0.16
    ting
    0.16
    Proof
    0.15
    aper
    0.15
     Train
    0.15
    Train
    0.15
    Act Density 0.019%

    No Known Activations