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

    Neuronpedia

    INDEX
    Explanations

    words related to distortion or misrepresentation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ciation
    -0.80
    ept
    -0.77
    autions
    -0.72
    fighters
    -0.72
    chal
    -0.72
    occup
    -0.71
    lication
    -0.70
    ailability
    -0.69
    oother
    -0.69
    alled
    -0.68
    POSITIVE LOGITS
     distorted
    0.85
     perceptions
    0.85
    adoes
    0.81
     distort
    0.75
     senses
    0.75
     interpretations
    0.74
     minds
    0.73
     disproportion
    0.72
     mund
    0.71
     versions
    0.70
    Act Density 0.111%

    No Known Activations