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

    Neuronpedia

    INDEX
    Explanations

    instances of past and present tense auxiliary verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lees
    -0.69
     Others
    -0.69
    Alert
    -0.67
    olor
    -0.67
    -+-+
    -0.67
    arine
    -0.66
    asionally
    -0.64
    Others
    -0.64
     Numerous
    -0.61
    Studies
    -0.60
    POSITIVE LOGITS
     instead
    0.70
     opted
    0.68
     understatement
    0.68
    instead
    0.67
    llah
    0.65
     caveat
    0.62
     emphasis
    0.61
     lucky
    0.60
    FAULT
    0.60
    iller
    0.59
    Act Density 0.124%

    No Known Activations