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

    Neuronpedia

    INDEX
    Explanations

    words related to negative emotions or strong opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    apons
    -0.80
    untled
    -0.73
    cliffe
    -0.72
    cipl
    -0.68
    ujah
    -0.67
    ngth
    -0.65
    Recommended
    -0.63
    haar
    -0.63
    usalem
    -0.63
    iencies
    -0.63
    POSITIVE LOGITS
     considering
    1.11
     coincidence
    0.86
     understatement
    0.80
     juxtap
    0.80
     hindsight
    0.80
     behold
    0.77
     imagine
    0.76
     nonetheless
    0.75
     retrospect
    0.71
     seeing
    0.71
    Act Density 6.233%

    No Known Activations