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

    Neuronpedia

    INDEX
    Explanations

    underscores and separators typically used in file names or paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    рост
    -0.55
    "><?=
    -0.54
    ]].
    -0.52
    ")))
    -0.52
    chevêque
    -0.51
     ResourceManager
    -0.48
     ${
    -0.48
     avan
    -0.47
    koning
    -0.46
     caro
    -0.45
    POSITIVE LOGITS
     myſelf
    1.07
     Monfieur
    1.07
     Jefus
    0.99
     raiſ
    0.98
     pleaſure
    0.98
     ſeveral
    0.97
     preſent
    0.97
     Anſ
    0.97
     Efq
    0.94
     Diſ
    0.92
    Act Density 0.079%

    No Known Activations