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

    Neuronpedia

    INDEX
    Explanations

    phrases related to destruction or removal

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to elimination or destruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.83
    aroo
    -0.78
    eele
    -0.75
    apter
    -0.75
    IOR
    -0.74
    SPONSORED
    -0.74
    nai
    -0.73
    ially
    -0.71
    tions
    -0.71
    ept
    -0.70
    POSITIVE LOGITS
     thunder
    0.78
     debris
    0.77
     rubble
    0.76
     virginity
    0.74
     asphalt
    0.74
     dust
    0.71
     ashes
    0.68
     Corpse
    0.68
     shards
    0.68
     powder
    0.67
    Act Density 0.379%

    No Known Activations