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

    Neuronpedia

    INDEX
    Explanations

    conjunctive phrases that connect ideas and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerPixel
    -0.17
    ELL
    -0.15
     Exact
    -0.14
    ungan
    -0.14
    iner
    -0.14
    ioxide
    -0.14
    ÑĤÑĮ
    -0.13
    ãĤ¹ãĥĨãĤ£
    -0.13
     abbrev
    -0.13
    /vnd
    -0.13
    POSITIVE LOGITS
    uhn
    0.17
    ylko
    0.17
    uate
    0.15
    aut
    0.14
    VML
    0.14
     vacancies
    0.14
    vac
    0.13
    illiseconds
    0.13
    ATTER
    0.13
    OrNil
    0.13
    Act Density 0.022%

    No Known Activations