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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "to be" in different forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shine
    -0.16
    ship
    -0.16
    untu
    -0.15
    abee
    -0.15
    ebo
    -0.15
    agma
    -0.15
    erah
    -0.14
    sh
    -0.14
    -envelope
    -0.14
    acks
    -0.14
    POSITIVE LOGITS
    -vous
    0.20
    ius
    0.16
    ió
    0.16
    eps
    0.16
    baum
    0.15
    chia
    0.15
    quiv
    0.14
    ski
    0.14
    vous
    0.14
    zÅij
    0.14
    Act Density 0.122%

    No Known Activations