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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific company named "Deloitte" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "Del" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     altogether
    -0.66
     stand
    -0.63
    ...]
    -0.62
     clipboard
    -0.61
    PsyNetMessage
    -0.61
     acting
    -0.59
    SHIP
    -0.57
     entirely
    -0.56
     fortune
    -0.56
     behind
    -0.56
    POSITIVE LOGITS
    phi
    1.41
    usional
    1.33
    ivered
    1.32
    ayed
    1.29
    ivering
    1.23
    icate
    1.23
    gado
    1.21
    aware
    1.15
    iber
    1.14
    aney
    1.11
    Act Density 0.012%

    No Known Activations