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

    Neuronpedia

    INDEX
    Explanations

    words related to something that has been a consistent or ongoing aspect or focus

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of continuity or permanence over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enary
    -0.72
     Rasm
    -0.71
    regate
    -0.71
     Allaah
    -0.67
    edi
    -0.66
     Awakens
    -0.65
    uin
    -0.64
     Cooldown
    -0.63
    ————————————————
    -0.63
    now
    -0.62
    POSITIVE LOGITS
     able
    1.08
     regarded
    1.06
     considered
    0.89
     fascinated
    0.85
     relegated
    0.84
     subjected
    0.81
     treated
    0.80
     credited
    0.76
     unable
    0.75
     intertwined
    0.75
    Act Density 0.130%

    No Known Activations