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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal experiences or insights

    oai_token-act-pair · gpt-3.5-turbo

    instances of "had" indicating past experiences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rift
    -0.64
    vp
    -0.62
    cade
    -0.61
    bery
    -0.59
    Enlarge
    -0.59
     retaining
    -0.58
    inducing
    -0.58
     toll
    -0.57
    Score
    -0.57
    Ess
    -0.56
    POSITIVE LOGITS
     hoped
    1.30
     heard
    1.13
     envisioned
    1.09
     dreamed
    1.06
     forgotten
    1.06
     imagined
    1.05
     nightmares
    1.04
     guessed
    0.99
     visions
    0.98
     doubts
    0.98
    Act Density 0.174%

    No Known Activations