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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and variables used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oref
    -0.17
    ocos
    -0.15
    одо
    -0.14
    olet
    -0.14
    strup
    -0.14
    elmet
    -0.14
    otel
    -0.14
     Cru
    -0.14
    éĹĺ
    -0.14
    ement
    -0.14
    POSITIVE LOGITS
    ge
    0.49
    le
    0.47
    gne
    0.30
    ne
    0.30
     ge
    0.28
    nge
    0.27
    gg
    0.25
    in
    0.23
    gt
    0.23
    ll
    0.22
    Act Density 0.073%

    No Known Activations