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

    Neuronpedia

    INDEX
    Explanations

    concepts related to mathematical structures and logic frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tuning
    -0.17
    het
    -0.16
    rzy
    -0.15
    Salvar
    -0.14
    /dataTables
    -0.14
    .flags
    -0.14
    ÑĤÑĮ
    -0.14
    ramer
    -0.14
    gettext
    -0.14
    hlas
    -0.14
    POSITIVE LOGITS
     Guards
    0.21
     Guard
    0.21
     stutter
    0.20
     Reach
    0.20
     trace
    0.18
     Bü
    0.18
     traces
    0.18
     Trace
    0.18
    reach
    0.17
     Transition
    0.17
    Act Density 0.089%

    No Known Activations