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

    Neuronpedia

    INDEX
    Explanations

    words related to time and events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in X," where X can be a variety of contexts or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wegian
    -0.65
    sle
    -0.64
    esh
    -0.63
    dar
    -0.61
     tied
    -0.60
     pegged
    -0.60
     ens
    -0.58
    casters
    -0.58
    llor
    -0.58
    Run
    -0.58
    POSITIVE LOGITS
     conjunction
    1.28
    effic
    1.21
    escap
    1.15
     vain
    1.11
     earnest
    1.08
     accordance
    1.08
    effect
    1.07
    roads
    1.07
     unison
    1.05
     tandem
    1.05
    Act Density 0.336%

    No Known Activations