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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to conceptual frameworks and theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    errat
    -0.17
    conc
    -0.17
    isher
    -0.16
    ÑĤеÑĢн
    -0.16
    oldem
    -0.16
    erin
    -0.15
    ardy
    -0.15
     magna
    -0.15
    alted
    -0.15
    rière
    -0.15
    POSITIVE LOGITS
    zza
    0.16
    mas
    0.15
    por
    0.15
     inse
    0.14
     ma
    0.14
    ãĤµãĤ¤
    0.14
    pel
    0.14
    ma
    0.14
    ../../../
    0.14
    aug
    0.14
    Act Density 0.018%

    No Known Activations