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

    Neuronpedia

    INDEX
    Explanations

    technical terms and functionality related to programming and request handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ì¿ł
    -0.16
    owell
    -0.16
    aldi
    -0.15
    éĤ¦
    -0.14
     FetchType
    -0.14
    quisa
    -0.14
     Bison
    -0.14
     Trudeau
    -0.14
    bourne
    -0.13
    Pod
    -0.13
    POSITIVE LOGITS
     reactor
    0.34
    react
    0.33
     twisted
    0.31
     Tw
    0.31
     reactors
    0.29
    -react
    0.28
     twist
    0.27
     twisting
    0.27
    tw
    0.27
     twists
    0.26
    Act Density 0.008%

    No Known Activations