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

    Neuronpedia

    INDEX
    Explanations

    words related to disguises and camouflage

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to disguises and concealment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ced
    -0.75
    raltar
    -0.74
    vals
    -0.71
    status
    -0.70
    aults
    -0.68
    xit
    -0.68
    ulz
    -0.65
    itar
    -0.65
    ERG
    -0.65
    20439
    -0.65
    POSITIVE LOGITS
     disgu
    1.23
     camoufl
    1.14
     disguise
    1.10
     disguised
    1.04
     camouflage
    0.95
     misunder
    0.87
    querade
    0.83
     conceal
    0.83
     hides
    0.80
     clo
    0.75
    Act Density 0.015%

    No Known Activations