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

    Neuronpedia

    INDEX
    Explanations

    words related to negative judgments or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of negative judgments or sentiments, particularly the word "terrible."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ership
    -0.86
    pai
    -0.86
    irs
    -0.85
    ilus
    -0.80
    aver
    -0.75
    eters
    -0.73
    cript
    -0.72
    paio
    -0.72
    izen
    -0.71
    gat
    -0.70
    POSITIVE LOGITS
     sounding
    0.81
     havoc
    0.78
    NESS
    0.77
     awful
    0.77
     nightmares
    0.76
     horrible
    0.75
     headache
    0.74
     nightmare
    0.73
     adolesc
    0.72
     ordeal
    0.72
    Act Density 0.022%

    No Known Activations