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

    Neuronpedia

    INDEX
    Explanations

    instances of common conjunctions and prepositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ambi
    -0.18
    ahren
    -0.15
    ãĥĨãĤ£
    -0.15
     doorstep
    -0.14
    ustum
    -0.14
    tron
    -0.14
    غÙĬÙĦ
    -0.14
    моÑĢ
    -0.14
    adius
    -0.13
    aden
    -0.13
    POSITIVE LOGITS
     riv
    0.17
    è³ŀ
    0.16
     words
    0.15
     points
    0.15
     distances
    0.15
    /view
    0.15
    DMI
    0.14
     thing
    0.14
     Gathering
    0.14
     male
    0.14
    Act Density 0.003%

    No Known Activations