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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "a [descriptor] [noun]" that relate to individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sti
    -0.18
    omu
    -0.15
    ston
    -0.15
    ARRIER
    -0.15
    crire
    -0.14
    leme
    -0.14
    imate
    -0.14
    .aw
    -0.14
    оваÑĢ
    -0.14
    umberland
    -0.13
    POSITIVE LOGITS
    ãĥ£
    0.14
    å¹³
    0.14
    ank
    0.14
    anko
    0.14
     Dut
    0.14
     man
    0.13
    ETH
    0.13
    un
    0.13
    _TOGGLE
    0.13
    nova
    0.13
    Act Density 0.160%

    No Known Activations