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

    Neuronpedia

    INDEX
    Explanations

    words related to social issues and challenges

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negative societal issues or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olid
    -0.72
    yna
    -0.66
     pione
    -0.65
    rael
    -0.65
    aphael
    -0.65
    cffffcc
    -0.64
    tesy
    -0.62
    estern
    -0.62
    future
    -0.61
    POST
    -0.61
    POSITIVE LOGITS
     THERE
    0.81
     there
    0.75
    there
    0.69
     temperatures
    0.65
     hairs
    0.65
     Defendants
    0.65
     owing
    0.64
     There
    0.64
     };
    0.62
     lacks
    0.62
    Act Density 0.485%

    No Known Activations