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

    Neuronpedia

    INDEX
    Explanations

    expressions related to criticism and confrontation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.73
    CLUS
    -0.71
     unchanged
    -0.70
    urdue
    -0.70
    USER
    -0.68
    ItemImage
    -0.66
     unaccompanied
    -0.64
    aepernick
    -0.64
    iae
    -0.62
    externalActionCode
    -0.62
    POSITIVE LOGITS
     feathers
    0.96
     horn
    0.91
     chops
    0.90
     horns
    0.86
     drum
    0.86
     crap
    0.86
     brim
    0.86
     punches
    0.86
     nose
    0.85
     finger
    0.84
    Act Density 3.543%

    No Known Activations