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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate additional information or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angered
    -0.16
    prung
    -0.16
     runaway
    -0.15
    seau
    -0.15
    uali
    -0.15
     NotSupportedException
    -0.14
     cÃłng
    -0.14
    737
    -0.14
    KER
    -0.14
     sic
    -0.13
    POSITIVE LOGITS
    avel
    0.18
     things
    0.17
     else
    0.17
    things
    0.15
     dut
    0.15
     Mor
    0.15
    vor
    0.15
     Elias
    0.14
    thing
    0.14
     reasons
    0.14
    Act Density 0.011%

    No Known Activations