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

    Neuronpedia

    INDEX
    Explanations

    phrases related to confirming or denying information

    oai_token-act-pair · gpt-3.5-turbo

    statements of confirmation or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onew
    -0.76
    enium
    -0.70
    ð
    -0.70
    psc
    -0.67
    cific
    -0.65
    perse
    -0.65
    brance
    -0.65
    pen
    -0.65
    bler
    -0.64
    theme
    -0.63
    POSITIVE LOGITS
     suspicions
    0.86
    atory
    0.82
    ations
    0.81
    orship
    0.80
     receipt
    0.79
     authenticity
    0.77
     sighting
    0.74
     rumours
    0.74
     sightings
    0.72
    ities
    0.72
    Act Density 0.047%

    No Known Activations