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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal or medical contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to perception and reality distortion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arel
    -0.44
    NetMessage
    -0.44
     WATCHED
    -0.40
     Cities
    -0.38
    odes
    -0.37
     Helpful
    -0.35
    olen
    -0.35
     stagnant
    -0.35
     satirical
    -0.35
    individual
    -0.35
    POSITIVE LOGITS
    eering
    0.56
    eers
    0.53
     thereof
    0.49
    smanship
    0.45
    ãĥ¼ãĥĨ
    0.43
    èĢħ
    0.43
    wagon
    0.42
    igible
    0.41
    arsity
    0.41
    uese
    0.41
    Act Density 1.876%

    No Known Activations