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

    Neuronpedia

    INDEX
    Explanations

    phrases related to human actions and events in past tense

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eway
    -0.69
    acies
    -0.68
    mong
    -0.68
    aic
    -0.67
    usat
    -0.64
    ¶ħ
    -0.64
    sonian
    -0.63
    avery
    -0.60
    ultane
    -0.58
     bitters
    -0.58
    POSITIVE LOGITS
    ],"
    0.61
    join
    0.61
    ipeg
    0.60
     them
    0.58
     Remem
    0.57
     Leopard
    0.57
     therap
    0.57
     nineteen
    0.55
     menstru
    0.55
     stride
    0.55
    Act Density 0.300%

    No Known Activations