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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and products

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific element in a system or environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spective
    -0.77
    direction
    -0.77
    sets
    -0.75
    credit
    -0.69
    pheus
    -0.67
     reconc
    -0.67
    clock
    -0.66
     Occupations
    -0.66
    yip
    -0.65
    perty
    -0.64
    POSITIVE LOGITS
    itudinal
    0.81
    itudes
    0.81
    orf
    0.81
    mann
    0.78
    robe
    0.76
    down
    0.76
    imes
    0.75
    acht
    0.74
    ounge
    0.73
    igue
    0.73
    Act Density 0.009%

    No Known Activations