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

    Neuronpedia

    INDEX
    Explanations

    words related to aggressive action or conflict

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "thrash" and its variations in the context of negative actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.84
    DEN
    -0.80
    enegger
    -0.79
     PowerPoint
    -0.67
    KEN
    -0.67
    ++++++++++++++++
    -0.66
    renheit
    -0.66
    dylib
    -0.65
     Marino
    -0.65
    WER
    -0.64
    POSITIVE LOGITS
    ifty
    1.09
    anches
    1.08
    inges
    1.04
    ashing
    1.04
    assi
    1.01
    uster
    1.00
    ongs
    0.96
    ift
    0.94
    ights
    0.94
    ace
    0.94
    Act Density 0.015%

    No Known Activations