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

    Neuronpedia

    INDEX
    Explanations

    mentions of problems and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulet
    -0.80
    urses
    -0.79
    alty
    -0.76
    rity
    -0.72
    rib
    -0.67
    ahon
    -0.67
    mosp
    -0.67
    odium
    -0.66
    ributes
    -0.66
     rib
    -0.66
    POSITIVE LOGITS
     solving
    1.20
     solved
    1.15
    olving
    1.02
     solve
    0.94
     plag
    0.94
    hooting
    0.92
    olved
    0.90
    atically
    0.88
     unsolved
    0.85
     posed
    0.85
    Act Density 0.029%

    No Known Activations