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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "I think that" expressing opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pione
    -0.80
    iped
    -0.75
    ä
    -0.74
    ascript
    -0.72
    RIP
    -0.72
    ãĤĬ
    -0.72
    afe
    -0.71
    oufl
    -0.70
    ãĤ´ãĥ³
    -0.70
    ombat
    -0.69
    POSITIVE LOGITS
    's
    1.26
     hasn
    0.96
     wasn
    0.95
    ÃŃs
    0.94
     doesn
    0.94
     qualifies
    0.92
     isn
    0.91
     depends
    0.91
     happens
    0.90
     constitutes
    0.90
    Act Density 0.243%

    No Known Activations