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

    Neuronpedia

    INDEX
    Explanations

    statements expressing personal beliefs or expectations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of beliefs or opinions from individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inary
    -0.72
    abi
    -0.69
    lite
    -0.65
    clock
    -0.64
    attle
    -0.60
     Written
    -0.60
    leness
    -0.60
    status
    -0.59
    commit
    -0.58
    Ware
    -0.58
    POSITIVE LOGITS
    olate
    0.68
    olated
    0.67
    iewicz
    0.59
     sclerosis
    0.58
     revival
    0.57
     SUN
    0.57
    phas
    0.56
    terson
    0.56
     suing
    0.56
    aspers
    0.56
    Act Density 0.210%

    No Known Activations