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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "collect" in various contexts

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

    Code or math-related content

    np_acts-logits-general · gemini-2.0-flash

    greatest common factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -1.85
     myſelf
    -1.82
     itſelf
    -1.72
    ſelf
    -1.64
     doubtnut
    -1.59
     Theſe
    -1.57
     Majefty
    -1.56
     purpoſe
    -1.56
     themſelves
    -1.56
    ſelves
    -1.53
    POSITIVE LOGITS
      
    0.87
     a
    0.82
     for
    0.81
     en
    0.81
     the
    0.81
     di
    0.78
     of
    0.78
     to
    0.78
     an
    0.76
     is
    0.76
    Act Density 0.199%

    No Known Activations