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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "saw" and its variants, indicating events or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contrace
    -0.72
     Adin
    -0.70
     Tanz
    -0.70
     shotgun
    -0.67
    ind
    -0.64
     sqor
    -0.61
    trap
    -0.60
     interviewing
    -0.59
     Zamb
    -0.58
     agric
    -0.58
    POSITIVE LOGITS
    Ĺ
    0.92
    awed
    0.90
    ei
    0.82
    eeper
    0.79
    rov
    0.78
    dust
    0.77
    yrs
    0.73
    lights
    0.71
    arnaev
    0.71
    angelo
    0.71
    Act Density 0.064%

    No Known Activations