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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "be" and phrases indicating potential or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vailability
    -0.16
    è¿·
    -0.15
    avern
    -0.15
     ilma
    -0.15
    venida
    -0.14
    avo
    -0.14
    alias
    -0.14
    roat
    -0.14
    éĥ¨
    -0.14
    ÑĢÑĥÑĩ
    -0.14
    POSITIVE LOGITS
    ibo
    0.16
    auf
    0.15
    за
    0.15
    enville
    0.14
    olis
    0.14
    dda
    0.14
    ibaba
    0.13
     ìŀIJìĦ¸
    0.13
     Investor
    0.13
    osy
    0.13
    Act Density 0.132%

    No Known Activations