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

    Neuronpedia

    INDEX
    Explanations

    phrases where a group or collective of people are being referred to

    oai_token-act-pair · gpt-3.5-turbo

    references to the perception of popularity or common opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibal
    -0.76
    acion
    -0.69
    fecture
    -0.67
    ipation
    -0.65
    ories
    -0.62
    uning
    -0.62
    ocol
    -0.62
    rompt
    -0.61
    aped
    -0.61
    ataka
    -0.60
    POSITIVE LOGITS
     observers
    0.93
     onlook
    0.89
    place
    0.85
     pundits
    0.79
     commentators
    0.77
    lees
    0.77
     passers
    0.76
     others
    0.76
     outsiders
    0.76
     attendees
    0.75
    Act Density 0.116%

    No Known Activations