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

    Neuronpedia

    INDEX
    Explanations

    phrases related to common sense

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to common sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quart
    -0.74
    Stars
    -0.73
    atern
    -0.72
    href
    -0.70
    RAW
    -0.70
    leased
    -0.68
    ISS
    -0.68
    reon
    -0.67
    âĸ¬âĸ¬
    -0.66
    ETA
    -0.65
    POSITIVE LOGITS
     dictates
    0.87
    smanship
    0.80
     chops
    0.75
     decency
    0.74
     constraints
    0.72
     ACTIONS
    0.72
     sensibilities
    0.71
    ensical
    0.69
     faculties
    0.69
     underpin
    0.68
    Act Density 0.058%

    No Known Activations