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

    Neuronpedia

    INDEX
    Explanations

    words related to actions, plans, or specific events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    izza
    -0.62
    anchester
    -0.61
    mite
    -0.60
    ãĤ´ãĥ³
    -0.60
    ruct
    -0.59
    igger
    -0.57
    odcast
    -0.56
     Offense
    -0.56
     Esports
    -0.55
    chuk
    -0.55
    POSITIVE LOGITS
     accordingly
    1.58
     consequently
    1.51
     therefore
    1.25
     thereafter
    1.21
     consequ
    1.19
     subsequently
    1.01
     alike
    0.98
     furthermore
    0.95
     moreover
    0.94
     thereby
    0.94
    Act Density 3.041%

    No Known Activations