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

    Neuronpedia

    INDEX
    Explanations

    inquiries about processes, definitions, and options related to specific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Disallow
    -0.16
    amina
    -0.16
    ansa
    -0.15
    combination
    -0.14
    bose
    -0.14
    OME
    -0.14
     Piece
    -0.14
     combination
    -0.14
    ycastle
    -0.14
    dess
    -0.14
    POSITIVE LOGITS
     types
    0.19
     exactly
    0.16
     Covered
    0.15
    çĢ¬
    0.15
     includ
    0.14
     covered
    0.14
    659
    0.14
    .isDefined
    0.14
     requ
    0.14
    -types
    0.14
    Act Density 0.055%

    No Known Activations