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

    Neuronpedia

    INDEX
    Explanations

    references to specific chemical classes and compounds

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     /\.
    -0.78
    bein
    -0.71
    ersham
    -0.71
     Bevan
    -0.71
    Bism
    -0.71
    ({\
    -0.69
     roś
    -0.68
     consommateurs
    -0.68
    ")->
    -0.67
     TURNER
    -0.67
    POSITIVE LOGITS
     Cla
    1.57
    Cla
    1.54
     cla
    1.52
    cla
    1.38
     Claude
    1.36
     CLA
    1.34
     clamps
    1.34
    Claude
    1.20
     Clau
    1.10
     Claw
    1.09
    Act Density 0.024%

    No Known Activations