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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Which."

    oai_token-act-pair · gpt-3.5-turbo

    questions or phrases that start with "Which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fried
    -0.77
    icable
    -0.70
    pees
    -0.69
    trained
    -0.68
    greg
    -0.68
     Antar
    -0.67
    limited
    -0.67
    mop
    -0.64
    perty
    -0.64
    UGE
    -0.64
    POSITIVE LOGITS
     brings
    1.29
     begs
    1.29
     leads
    1.00
     means
    0.97
     raises
    0.93
     reminds
    0.92
     sucks
    0.90
     translates
    0.87
     sounds
    0.86
     prompts
    0.85
    Act Density 0.048%

    No Known Activations