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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doors
    -0.19
    oriously
    -0.19
    semble
    -0.19
    lights
    -0.17
    mans
    -0.16
    mediate
    -0.16
    rox
    -0.16
    soon
    -0.16
    recht
    -0.16
    hammad
    -0.15
    POSITIVE LOGITS
    heading
    0.28
    aming
    0.27
    arded
    0.27
    ech
    0.26
    aded
    0.25
    anie
    0.25
    hest
    0.25
    acons
    0.25
    aver
    0.24
    eh
    0.23
    Act Density 0.016%

    No Known Activations