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

    Neuronpedia

    INDEX
    Explanations

    words related to significant life events and changes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    share
    -0.81
    gang
    -0.80
    border
    -0.80
    SHARE
    -0.79
    upper
    -0.79
    pet
    -0.77
    putable
    -0.76
    tiny
    -0.76
    employed
    -0.75
    lang
    -0.75
    POSITIVE LOGITS
     innovations
    0.83
     measures
    0.81
     interventions
    0.80
     consequences
    0.78
     attraction
    0.77
     attractions
    0.77
     feats
    0.77
     insights
    0.75
     enhancements
    0.75
     splash
    0.75
    Act Density 0.099%

    No Known Activations