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

    Neuronpedia

    INDEX
    Explanations

    references to a specific name "Dorner"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named Dor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.80
    unct
    -0.69
    episode
    -0.68
     Terrorism
    -0.67
    unction
    -0.67
    testing
    -0.66
    heet
    -0.65
    ulative
    -0.65
    WAYS
    -0.64
    uncture
    -0.63
    POSITIVE LOGITS
     Dor
    1.06
    cas
    0.95
    ÃŃa
    0.93
    iane
    0.91
    oshenko
    0.85
    je
    0.85
    ado
    0.82
    chester
    0.81
    idad
    0.79
    adan
    0.79
    Act Density 0.004%

    No Known Activations