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

    Neuronpedia

    INDEX
    Explanations

    mentions of written works such as memoirs, autobiographies, and diaries

    oai_token-act-pair · gpt-3.5-turbo

    references to memoirs and autobiographies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aid
    -0.72
    OPA
    -0.70
     constitu
    -0.68
    upid
    -0.65
    cone
    -0.64
     Pearson
    -0.64
    Sensor
    -0.63
    axis
    -0.63
     Definition
    -0.61
    fly
    -0.60
    POSITIVE LOGITS
     memoir
    1.17
    oir
    0.92
     autobiography
    0.91
    spective
    0.91
     autobi
    0.89
    spection
    0.84
    ously
    0.83
    izes
    0.79
    writer
    0.78
    orial
    0.78
    Act Density 0.022%

    No Known Activations