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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative emotions

    oai_token-act-pair · gpt-3.5-turbo

    words that denote negative states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.71
     Catalyst
    -0.67
    Merit
    -0.66
     fencing
    -0.61
     Luigi
    -0.57
     runway
    -0.57
    frame
    -0.56
     Quadro
    -0.54
     Frames
    -0.54
     box
    -0.54
    POSITIVE LOGITS
    ciating
    0.81
    eful
    0.77
    ctions
    0.75
    rums
    0.72
    efully
    0.70
    terness
    0.70
    cemic
    0.69
    itory
    0.69
    ctive
    0.69
    iveness
    0.68
    Act Density 0.117%

    No Known Activations