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

    Neuronpedia

    INDEX
    Explanations

    words related to desperation and urgency

    oai_token-act-pair · gpt-3.5-turbo

    words related to performance metrics or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategory
    -0.69
    ESCO
    -0.62
     href
    -0.61
    ADRA
    -0.60
    76561
    -0.60
    krit
    -0.58
    ourt
    -0.58
    ellen
    -0.58
     QR
    -0.57
    akes
    -0.56
    POSITIVE LOGITS
    manent
    1.09
    due
    1.05
    monkey
    0.94
    nel
    0.94
    intendent
    0.94
    cussion
    0.91
    stein
    0.90
    ior
    0.85
    ium
    0.85
    vasive
    0.83
    Act Density 0.026%

    No Known Activations