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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communities or groups and their activities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to various communities and their sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Miss
    -0.76
     omission
    -0.71
    zeb
    -0.69
     apologise
    -0.67
    umatic
    -0.66
    POSE
    -0.65
    stroke
    -0.64
     stroke
    -0.64
     Mehran
    -0.63
     Delivery
    -0.63
    POSITIVE LOGITS
     coales
    1.05
     comprised
    0.90
     united
    0.88
    Unity
    0.87
     receptive
    0.83
     unified
    0.79
     overwhelmingly
    0.79
     populated
    0.78
    represented
    0.78
     cohesive
    0.78
    Act Density 0.648%

    No Known Activations