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

    Neuronpedia

    INDEX
    Explanations

    phrases related to modifications or alterations

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

    making changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.63
    bibitem
    -0.40
    ayuno
    -0.40
     مرئيه
    -0.39
    racene
    -0.39
     Weiner
    -0.38
     infection
    -0.38
    Espèce
    -0.36
    __((
    -0.36
    rickson
    -0.36
    POSITIVE LOGITS
    Modify
    0.65
    modify
    0.64
     modifications
    0.64
    changes
    0.63
     Changes
    0.63
     Modifications
    0.63
     tweaks
    0.62
     modifying
    0.62
    Modifications
    0.61
    Changes
    0.61
    Act Density 0.023%

    No Known Activations