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

    Neuronpedia

    INDEX
    Explanations

    terms related to criticism or negative sentiment towards a particular situation or action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.77
     Corpus
    -0.73
    eer
    -0.69
    ISM
    -0.67
    SHIP
    -0.67
    yip
    -0.66
     Nun
    -0.65
    eering
    -0.65
     Pose
    -0.64
    law
    -0.63
    POSITIVE LOGITS
    agons
    1.17
    inking
    1.16
    ags
    1.12
    unk
    1.11
    unks
    1.10
    udge
    1.10
    ifts
    1.10
    inks
    1.09
    iller
    1.07
    aining
    1.05
    Act Density 0.072%

    No Known Activations