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

    Neuronpedia

    INDEX
    Explanations

    comparative terms indicating a contrast or comparison

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

    comparisons using versus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prêtres
    -0.59
     ainfi
    -0.57
    AxisAlignment
    -0.55
     informée
    -0.54
     Rept
    -0.53
    ⓧ
    -0.51
    MethodManager
    -0.50
    oustic
    -0.50
    ldg
    -0.49
     appelez
    -0.49
    POSITIVE LOGITS
     versus
    1.63
    versus
    1.38
     Versus
    1.34
    Versus
    1.19
     VERS
    0.75
     beziehungs
    0.59
    ものに
    0.56
     opposite
    0.54
    ="#">
    0.53
     minus
    0.53
    Act Density 0.016%

    No Known Activations