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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values and their relationships within technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ../../../
    -0.21
    fold
    -0.20
    ../../
    -0.17
    acho
    -0.17
    rd
    -0.17
    elson
    -0.17
    -quarters
    -0.17
    /current
    -0.16
    iy
    -0.16
    utan
    -0.16
    POSITIVE LOGITS
    nd
    0.52
    nds
    0.27
    ND
    0.26
    -thirds
    0.24
    nde
    0.21
    nder
    0.21
    857
    0.20
     thirds
    0.20
    нд
    0.20
    nda
    0.18
    Act Density 0.183%

    No Known Activations