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

    Neuronpedia

    INDEX
    Explanations

    references to late-night talk shows and their hosts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agara
    -0.18
    žit
    -0.17
    eren
    -0.15
    hr
    -0.15
    lassen
    -0.15
    quam
    -0.15
    ockey
    -0.14
    irus
    -0.14
     ther
    -0.14
    istrat
    -0.14
    POSITIVE LOGITS
    @dynamic
    0.17
     lô
    0.16
    undefined
    0.16
    Undefined
    0.15
    aches
    0.15
    elder
    0.15
    -д
    0.15
    ãĥ³ãĥĨ
    0.14
    uncate
    0.14
    etti
    0.14
    Act Density 0.047%

    No Known Activations