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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "be" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ABCDEFGHI
    -0.15
    utsch
    -0.15
    eneric
    -0.15
     Sharing
    -0.14
     varying
    -0.14
    ξι
    -0.13
    urname
    -0.13
    ior
    -0.13
     descending
    -0.13
    emade
    -0.13
    POSITIVE LOGITS
     instrumental
    0.30
     responsible
    0.29
    instrument
    0.27
     able
    0.26
     determinant
    0.21
     reflected
    0.21
     responsable
    0.20
     key
    0.20
     Able
    0.19
     used
    0.19
    Act Density 0.262%

    No Known Activations