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

    Neuronpedia

    INDEX
    Explanations

    phrases related to words that contain the prefix "sub-"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "sub" followed by any term indicating a category or theme, often in a critical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reloaded
    -0.67
     Mercy
    -0.64
     destro
    -0.63
     dearly
    -0.63
     flared
    -0.62
     Graveyard
    -0.61
     ahead
    -0.61
     behind
    -0.61
     preceded
    -0.60
     Polk
    -0.59
    POSITIVE LOGITS
    Saharan
    1.56
    contract
    1.36
    committee
    1.35
    paragraph
    1.33
    division
    1.32
    surface
    1.32
    section
    1.29
    national
    1.29
    zero
    1.28
    continental
    1.27
    Act Density 0.016%

    No Known Activations