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

    Neuronpedia

    INDEX
    Explanations

    unique symbols or characters used in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     programmes
    -0.18
    strup
    -0.15
    elite
    -0.15
     Terror
    -0.15
    Singapore
    -0.15
     Singap
    -0.15
    elsen
    -0.15
     programme
    -0.14
     singapore
    -0.14
     Pron
    -0.14
    POSITIVE LOGITS
     Jar
    0.29
     Bell
    0.27
     Meadows
    0.26
    Jar
    0.25
     Meadow
    0.23
     East
    0.23
     Council
    0.23
    Bell
    0.23
    East
    0.20
     jar
    0.20
    Act Density 0.003%

    No Known Activations