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

    Neuronpedia

    INDEX
    Explanations

    words related to negative emotions like shame, guilt, pity, anger, and judgment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of shame and related emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enhagen
    -0.82
    ersive
    -0.79
    ichick
    -0.73
    agall
    -0.73
    ancial
    -0.72
    aeda
    -0.70
    IFE
    -0.69
    irements
    -0.68
    agnetic
    -0.67
    ighters
    -0.65
    POSITIVE LOGITS
    faced
    1.33
    fully
    1.30
    face
    1.00
    fulness
    0.99
    imaru
    0.97
    ously
    0.93
    ful
    0.93
     Shame
    0.90
     shame
    0.90
     judgement
    0.82
    Act Density 0.044%

    No Known Activations