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

    Neuronpedia

    INDEX
    Explanations

    phrases related to increasingly negative situations or developments

    oai_token-act-pair · gpt-3.5-turbo

    negative outcomes and deteriorating situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.79
    ools
    -0.72
    iciency
    -0.70
    obook
    -0.65
    icrobial
    -0.65
    rity
    -0.63
    arlane
    -0.63
    gemony
    -0.60
    phies
    -0.60
    rahim
    -0.59
    POSITIVE LOGITS
     roy
    0.82
     backstage
    0.79
     ¯
    0.75
    ./
    0.75
     downhill
    0.73
    ansky
    0.72
     for
    0.72
     diplom
    0.71
     brewing
    0.67
     Kenobi
    0.66
    Act Density 0.181%

    No Known Activations