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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and prepositions in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -
    -0.15
    ines
    -0.14
    ings
    -0.14
     Morav
    -0.13
    ness
    -0.13
    .BL
    -0.13
    lei
    -0.13
     DC
    -0.13
    mania
    -0.13
    (s
    -0.13
    POSITIVE LOGITS
    uten
    0.17
    setattr
    0.16
    anja
    0.16
    dash
    0.16
    isson
    0.15
    æĸ¯çī¹
    0.14
    hta
    0.14
    мовÑĸÑĢ
    0.14
    oine
    0.14
    ivatel
    0.14
    Act Density 0.101%

    No Known Activations