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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating doubt or questioning of validity in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    many
    -0.61
     leider
    -0.60
     many
    -0.58
     very
    -0.57
     disponibilités
    -0.53
     Many
    -0.53
     zwar
    -0.53
    very
    -0.52
    meist
    -0.51
    Many
    -0.51
    POSITIVE LOGITS
     quelconque
    1.26
     jemals
    1.06
     anything
    0.99
     anybody
    0.89
     any
    0.86
     irgende
    0.86
    anything
    0.86
     anyone
    0.83
     aught
    0.82
     quelcon
    0.80
    Act Density 0.636%

    No Known Activations