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

    Neuronpedia

    INDEX
    Explanations

    words related to specification or identification

    oai_token-act-pair · gpt-3.5-turbo

    words related to scientific concepts or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.70
    CTV
    -0.69
    PRES
    -0.67
     EntityItem
    -0.66
     Boots
    -0.64
    RS
    -0.63
     Sach
    -0.63
     Rack
    -0.62
    JP
    -0.62
     Targ
    -0.61
    POSITIVE LOGITS
    ific
    1.51
    atory
    1.17
    ulty
    1.07
    ially
    1.00
    ature
    0.99
    ally
    0.98
    ual
    0.97
    iation
    0.94
    urus
    0.93
    ificent
    0.93
    Act Density 0.010%

    No Known Activations