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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    contres
    -0.17
    ilogy
    -0.15
    gence
    -0.15
    rema
    -0.14
    ication
    -0.14
    anco
    -0.14
    licative
    -0.14
    å«Į
    -0.14
    ilin
    -0.14
    jak
    -0.14
    POSITIVE LOGITS
    ’t
    0.18
    't
    0.18
     easily
    0.16
    onic
    0.15
     saja
    0.15
    862
    0.15
    adians
    0.15
    903
    0.14
    noinspection
    0.14
    ldr
    0.14
    Act Density 0.069%

    No Known Activations