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

    Neuronpedia

    INDEX
    Explanations

    descriptive words conveying a negative characteristic or feeling

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "nasty" and related negative descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HCR
    -0.85
    inet
    -0.83
    ingham
    -0.82
    inoa
    -0.76
    ETF
    -0.76
    aver
    -0.75
    produced
    -0.74
    inez
    -0.73
    oning
    -0.72
    Particip
    -0.72
    POSITIVE LOGITS
     nasty
    1.15
     surprises
    1.03
     adolesc
    1.02
     earthqu
    0.87
     spoil
    0.85
     ugly
    0.83
     undermin
    0.79
     poisonous
    0.79
     beasts
    0.77
     smelling
    0.77
    Act Density 0.010%

    No Known Activations