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

    Neuronpedia

    INDEX
    Explanations

    instances of statements related to rights or privileges

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to rights and opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammers
    -0.87
    lees
    -0.85
    errors
    -0.83
    iddles
    -0.79
    misc
    -0.78
    storms
    -0.77
    missions
    -0.75
    recent
    -0.75
    anders
    -0.74
    hops
    -0.73
    POSITIVE LOGITS
     clue
    1.14
     glimpse
    1.14
     reminder
    1.14
     piece
    1.12
     doorway
    1.10
     protector
    1.09
     paycheck
    1.09
     semblance
    1.05
     thing
    1.05
     conduit
    1.05
    Act Density 0.416%

    No Known Activations