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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to mathematical definitions and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouden
    -0.15
     Fallon
    -0.15
    ej
    -0.14
    oret
    -0.14
    erg
    -0.14
    erring
    -0.13
    campo
    -0.13
     Sheridan
    -0.13
    avers
    -0.13
    opt
    -0.13
    POSITIVE LOGITS
     Exercise
    0.16
    .interfaces
    0.14
     Wol
    0.14
     rfl
    0.14
     precisely
    0.14
    KHR
    0.14
     fanc
    0.13
    Exercise
    0.13
     Zar
    0.13
    ulis
    0.13
    Act Density 0.056%

    No Known Activations