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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sending communication or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "sent out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.65
    cious
    -0.64
    cius
    -0.62
     Primordial
    -0.61
    phrine
    -0.60
    hetti
    -0.58
     Locked
    -0.58
     warmed
    -0.58
     exposed
    -0.58
     gou
    -0.57
    POSITIVE LOGITS
    stretched
    0.96
    posts
    0.78
    spread
    0.77
    rists
    0.75
    fitted
    0.75
    doors
    0.73
    rils
    0.71
    smart
    0.68
    sole
    0.68
    )=(
    0.66
    Act Density 0.056%

    No Known Activations