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

    Neuronpedia

    INDEX
    Explanations

    words related to concepts of separation or isolation

    oai_token-act-pair · gpt-3.5-turbo

    words related to insensitivity or insulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.70
     Master
    -0.70
     Sabha
    -0.67
     XD
    -0.67
    ries
    -0.66
    ARK
    -0.65
     Scotia
    -0.65
    ãĥ£
    -0.65
    goers
    -0.64
     Kavanaugh
    -0.64
    POSITIVE LOGITS
    ensible
    1.19
    urances
    1.10
    pite
    1.07
    istent
    1.06
    ensibly
    1.03
    semb
    1.01
    ufficient
    0.98
    uper
    0.96
    criptions
    0.95
    ides
    0.94
    Act Density 0.010%

    No Known Activations