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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal relationships and interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of trades and exchanges in contexts involving sports or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Consider
    -0.65
    ithering
    -0.65
    illions
    -0.62
    pport
    -0.61
    polit
    -0.60
     ticking
    -0.59
    udic
    -0.57
     unimagin
    -0.56
    erity
    -0.55
    tty
    -0.55
    POSITIVE LOGITS
     she
    0.91
     he
    0.85
     they
    0.81
     Lopez
    0.79
     Neal
    0.75
     Meow
    0.73
     him
    0.72
     Garcia
    0.72
     Sawyer
    0.72
    she
    0.71
    Act Density 0.898%

    No Known Activations