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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting cues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    among

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.73
     queſta
    -0.64
     myſelf
    -0.59
    ſelf
    -0.57
    parsedMessage
    -0.56
     Roskov
    -0.56
    ſelves
    -0.56
    >\<^
    -0.55
     ujednoznacz
    -0.55
    WindowConstants
    -0.54
    POSITIVE LOGITS
     Among
    0.41
     among
    0.39
    three
    0.38
    Among
    0.38
    among
    0.36
     parmi
    0.36
    +#+
    0.35
    RRect
    0.35
     three
    0.34
    chief
    0.34
    Act Density 0.047%

    No Known Activations