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

    Neuronpedia

    INDEX
    Explanations

    references to specific programming tools or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PointSize
    -0.15
    ulpt
    -0.15
    yonel
    -0.15
    icari
    -0.15
    hare
    -0.15
    ksiyon
    -0.14
    ©
    -0.14
    ascar
    -0.14
    estar
    -0.14
    olis
    -0.14
    POSITIVE LOGITS
    iju
    0.16
     Bates
    0.15
    505
    0.15
    नल
    0.14
    _terminal
    0.14
    yme
    0.14
     sto
    0.14
    fol
    0.13
     Roll
    0.13
     pros
    0.13
    Act Density 0.005%

    No Known Activations