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

    Neuronpedia

    INDEX
    Explanations

    references to data analysis and calculations related to metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Willie
    -0.15
    AILS
    -0.15
    .scene
    -0.15
    å¯Ħ
    -0.14
    erald
    -0.14
     sand
    -0.14
    à¸ij
    -0.14
    clamation
    -0.13
    ullan
    -0.13
    etak
    -0.13
    POSITIVE LOGITS
     formula
    0.31
     cell
    0.29
     formulas
    0.29
     cells
    0.28
    formula
    0.28
     Formula
    0.25
     Cell
    0.25
    Formula
    0.24
     Cells
    0.24
     range
    0.23
    Act Density 0.029%

    No Known Activations