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

    Neuronpedia

    INDEX
    Explanations

    words related to emotions of dissatisfaction or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    expressions of dissatisfaction or negative sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YES
    -0.73
    azar
    -0.69
    gdala
    -0.68
    ortment
    -0.68
    oubted
    -0.65
     ACTIONS
    -0.63
    articles
    -0.62
    ython
    -0.61
    doms
    -0.61
    maximum
    -0.61
    POSITIVE LOGITS
     anymore
    1.61
     nor
    1.09
    yet
    0.99
     yet
    0.93
     Enough
    0.74
     enough
    0.72
     necessarily
    0.72
     bothered
    0.71
     whatsoever
    0.70
    Ú
    0.70
    Act Density 0.193%

    No Known Activations