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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" across various tenses and grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intervening
    -0.15
    noinspection
    -0.15
    dál
    -0.15
    /release
    -0.14
     Outs
    -0.14
     Äijình
    -0.14
     obsc
    -0.14
    exe
    -0.13
    emi
    -0.13
    .xmlbeans
    -0.13
    POSITIVE LOGITS
     needed
    0.16
    needed
    0.16
     enough
    0.16
    -ÑĤо
    0.15
     necessary
    0.15
     eas
    0.15
     used
    0.15
     what
    0.14
    necessary
    0.14
    agoon
    0.14
    Act Density 0.717%

    No Known Activations