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

    Neuronpedia

    INDEX
    Explanations

    references to specific programming or database terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pin
    -0.80
    pet
    -0.79
    ping
    -0.76
    pla
    -0.76
    pan
    -0.75
    pat
    -0.74
    pot
    -0.73
    pers
    -0.73
    parse
    -0.72
    pun
    -0.71
    POSITIVE LOGITS
     P
    1.20
     p
    1.14
     getP
    1.12
     Po
    0.94
     PL
    0.91
     П
    0.90
     PO
    0.89
     Pl
    0.87
     po
    0.86
     PA
    0.83
    Act Density 0.294%

    No Known Activations