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

    Neuronpedia

    INDEX
    Explanations

    various forms of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alo
    -0.16
    olib
    -0.15
    á»ģ
    -0.15
     oltre
    -0.14
    ationale
    -0.14
    .FontStyle
    -0.14
    urn
    -0.14
    zyst
    -0.14
    olor
    -0.14
    ieurs
    -0.14
    POSITIVE LOGITS
     through
    0.27
     thanks
    0.26
     upon
    0.24
     during
    0.24
     when
    0.22
     precisely
    0.21
     these
    0.21
    thanks
    0.21
     via
    0.20
     because
    0.20
    Act Density 0.078%

    No Known Activations