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

    Neuronpedia

    INDEX
    Explanations

    references to partial ownership or contribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mostly
    -0.26
     mainly
    -0.23
     primarily
    -0.20
    mostly
    -0.20
    sole
    -0.18
     predominantly
    -0.18
     principalmente
    -0.18
    inkel
    -0.18
     chiefly
    -0.17
     basically
    -0.17
    POSITIVE LOGITS
     responsible
    0.19
     because
    0.16
     due
    0.15
    akers
    0.15
     Because
    0.14
    ãģıãĤĭ
    0.14
    Because
    0.14
    aque
    0.14
     olmak
    0.14
     Coll
    0.13
    Act Density 0.028%

    No Known Activations