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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possibility or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating possibility or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gets
    -0.69
     Nanto
    -0.68
    DAQ
    -0.65
    ashes
    -0.62
     dies
    -0.61
    loads
    -0.61
    efeated
    -0.60
    OV
    -0.59
     Fug
    -0.58
     Nev
    -0.57
    POSITIVE LOGITS
     signify
    1.31
     represent
    1.26
     relate
    1.23
     indicate
    1.15
     imply
    1.12
     be
    1.12
     originate
    1.12
     explain
    1.09
     reflect
    1.05
     belong
    1.05
    Act Density 0.109%

    No Known Activations