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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "approve" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ums
    -0.07
    cape
    -0.07
    ette
    -0.07
    are
    -0.07
    /do
    -0.07
    idl
    -0.06
    -browser
    -0.06
    irst
    -0.06
    issen
    -0.06
    c
    -0.06
    POSITIVE LOGITS
    ably
    0.10
    able
    0.07
     Ansi
    0.07
    VERTISEMENT
    0.07
    ance
    0.07
    amu
    0.07
    amet
    0.07
    -ÑĤаки
    0.07
    égor
    0.07
    buquerque
    0.07
    Act Density 0.014%

    No Known Activations