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

    Neuronpedia

    INDEX
    Explanations

    references to the automated or automated-like behavior of systems or processes

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     Automatic
    -1.53
    Automatic
    -1.52
    automatic
    -1.48
     automatic
    -1.43
     Automated
    -1.35
     automat
    -1.29
     Automat
    -1.28
     automática
    -1.25
     automated
    -1.24
    Automated
    -1.23
    POSITIVE LOGITS
     auto
    0.95
     car
    0.63
    iddle
    0.56
    irchen
    0.55
     verfolgt
    0.54
     barba
    0.54
    ValueStyle
    0.54
     diss
    0.53
     propa
    0.52
     समीक्षक
    0.52
    Act Density 0.005%

    No Known Activations