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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antino
    -0.16
    uis
    -0.15
     adulti
    -0.15
    eton
    -0.15
    IGH
    -0.15
    overy
    -0.15
    наÑħ
    -0.15
    amilia
    -0.14
    baugh
    -0.14
    ller
    -0.14
    POSITIVE LOGITS
     assigned
    0.19
     approached
    0.19
     intent
    0.18
     m
    0.18
     tail
    0.18
     visited
    0.18
     sent
    0.17
     thrust
    0.17
     introduced
    0.17
     bro
    0.17
    Act Density 0.115%

    No Known Activations