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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the importance or significance of roles played by entities in various scenarios

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the significance or impact of various factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atri
    -0.69
    arus
    -0.68
    Lev
    -0.67
    agle
    -0.65
     wings
    -0.61
    bryce
    -0.61
     roomm
    -0.61
    ft
    -0.59
    ©¶æ
    -0.59
    Tok
    -0.59
    POSITIVE LOGITS
     determining
    0.80
     helping
    0.78
    lycer
    0.74
     role
    0.71
     facilitating
    0.70
     assisting
    0.67
     shaping
    0.66
     toward
    0.66
     educating
    0.65
     whatsoever
    0.65
    Act Density 0.051%

    No Known Activations