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

    Neuronpedia

    INDEX
    Explanations

    sentences that include forms of the verb "to be" and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.20
    ông
    -0.16
    boom
    -0.16
    chet
    -0.15
     Nobel
    -0.15
    mpz
    -0.14
    /arch
    -0.14
    ä¸Ģä¸ĭ
    -0.14
    roe
    -0.14
    pivot
    -0.13
    POSITIVE LOGITS
     active
    0.22
     currently
    0.21
     widely
    0.19
     Currently
    0.18
     married
    0.18
     past
    0.18
     vice
    0.18
     particularly
    0.17
     proud
    0.17
    Currently
    0.17
    Act Density 0.062%

    No Known Activations