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

    Neuronpedia

    INDEX
    Explanations

    elements related to diagrammatic representations and transitions in a system setup

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

    Comes after "Change" or a symbol

    np_acts-logits-general · gemini-2.0-flash

    Change PA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -1.07
     ainfi
    -1.03
     Majefty
    -1.01
     Houſe
    -1.00
     étoient
    -0.97
     feroit
    -0.95
     ་་
    -0.94
     Theſe
    -0.92
     Shakspeare
    -0.91
     auroit
    -0.91
    POSITIVE LOGITS
     again
    0.59
     multiple
    0.58
     non
    0.58
     
    0.58
     second
    0.57
     B
    0.57
    less
    0.56
     en
    0.56
     per
    0.55
     T
    0.54
    Act Density 3.583%

    No Known Activations