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

    Neuronpedia

    INDEX
    Explanations

    phrases related to irony and contradictions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noc
    -0.16
    Ŀ
    -0.15
    flux
    -0.14
    enberg
    -0.14
    Ñģп
    -0.14
    ritch
    -0.14
    brit
    -0.13
    ãĥ¼ãĥ«ãĥī
    -0.13
    ining
    -0.13
     fab
    -0.13
    POSITIVE LOGITS
    .scalablytyped
    0.18
    buz
    0.18
     subrange
    0.16
    ozor
    0.15
    VERTISE
    0.15
    PCP
    0.14
    porto
    0.14
    .updateDynamic
    0.13
    NCY
    0.13
    EFR
    0.13
    Act Density 1.047%

    No Known Activations