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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating exceptions or caveats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aser
    -0.15
    gien
    -0.15
    curso
    -0.15
    aven
    -0.15
     Harness
    -0.14
    amura
    -0.14
    æģµ
    -0.14
    rin
    -0.13
     Rin
    -0.13
    AKE
    -0.13
    POSITIVE LOGITS
    rud
    0.16
    ursal
    0.15
     Erf
    0.15
    475
    0.15
     Lambert
    0.14
    lád
    0.14
    ifes
    0.14
    æk
    0.14
     Trit
    0.14
     Skipping
    0.13
    Act Density 0.049%

    No Known Activations