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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and their occurrences in various grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    halt
    -0.15
    utschen
    -0.15
    verts
    -0.15
    pler
    -0.14
    avs
    -0.13
    onga
    -0.13
    acht
    -0.13
    acades
    -0.13
     неÑĤ
    -0.13
    flip
    -0.13
    POSITIVE LOGITS
    opi
    0.15
     TMPro
    0.13
     happen
    0.13
    JM
    0.13
    ACES
    0.13
    icensed
    0.13
     happened
    0.13
    -ÑĤ
    0.13
    idla
    0.13
    onom
    0.12
    Act Density 0.045%

    No Known Activations