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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses

    oai_token-act-pair · gpt-3.5-turbo

    affirmations or confirmations regarding various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bage
    -0.87
    recated
    -0.70
    Offline
    -0.67
     ILCS
    -0.67
    leted
    -0.66
    RAW
    -0.65
    rarily
    -0.65
    ufact
    -0.61
    killer
    -0.61
    cheon
    -0.60
    POSITIVE LOGITS
    terday
    1.72
    YES
    0.78
     sir
    0.76
    yne
    0.73
    yes
    0.72
    sis
    0.69
     matter
    0.69
    eed
    0.68
    ñ
    0.67
     Deal
    0.66
    Act Density 0.020%

    No Known Activations