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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    geographical features and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unethical
    -0.72
     bullying
    -0.71
     impuls
    -0.70
     accuser
    -0.68
     Deadpool
    -0.68
     coercion
    -0.68
     dismissing
    -0.68
     inappropriately
    -0.68
     Seth
    -0.67
     torture
    -0.66
    POSITIVE LOGITS
    Located
    1.13
     limestone
    1.02
     inland
    0.95
     tallest
    0.94
     tourist
    0.93
     asphalt
    0.93
     Located
    0.93
     southwestern
    0.92
     kilomet
    0.92
     mountainous
    0.87
    Act Density 1.488%

    No Known Activations