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

    Neuronpedia

    INDEX
    Explanations

    words related to irritation or annoyance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     redemption
    -0.66
    ffen
    -0.64
     Dani
    -0.63
     reconciliation
    -0.63
     Syri
    -0.61
     redes
    -0.60
    suit
    -0.58
     Prison
    -0.57
    fter
    -0.57
    FOR
    -0.57
    POSITIVE LOGITS
    ants
    1.31
    encies
    1.20
    ant
    1.16
    antly
    1.13
    abulary
    1.10
    ative
    1.07
    ency
    1.07
    ately
    1.01
    ably
    1.00
    ables
    0.99
    Act Density 0.010%

    No Known Activations