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

    Neuronpedia

    INDEX
    Explanations

    phrases related to persistence and continuation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    acus
    -0.86
    atana
    -0.81
    DragonMagazine
    -0.81
    ointed
    -0.79
    ode
    -0.78
    ooter
    -0.77
    KEN
    -0.77
    Interstitial
    -0.76
    ombat
    -0.75
    NetMessage
    -0.74
    POSITIVE LOGITS
     tabs
    1.33
     pace
    1.12
     track
    1.11
     secrets
    1.07
     afloat
    1.07
     vigil
    0.98
    tracks
    0.97
     alive
    0.90
     quiet
    0.88
     breathing
    0.86
    Act Density 9.332%

    No Known Activations