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

    Neuronpedia

    INDEX
    Explanations

    references to introductory phrases or sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tas
    -0.18
    duct
    -0.17
    eries
    -0.16
    bon
    -0.15
    ordin
    -0.15
    ires
    -0.15
    /about
    -0.15
    sofar
    -0.15
    ographically
    -0.14
    IFF
    -0.14
    POSITIVE LOGITS
    iciar
    0.19
    eview
    0.17
    gle
    0.16
    imary
    0.16
    antry
    0.15
    amins
    0.14
    ngr
    0.14
    IMIT
    0.14
    ÃŃcio
    0.14
    inez
    0.14
    Act Density 0.116%

    No Known Activations