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

    Neuronpedia

    INDEX
    Explanations

    references to experts and expert-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cloth
    -0.16
    arella
    -0.16
    eras
    -0.16
    person
    -0.16
    wright
    -0.15
    boarding
    -0.15
    agra
    -0.15
    woord
    -0.15
    iani
    -0.15
    gaard
    -0.15
    POSITIVE LOGITS
    ise
    0.31
    ises
    0.25
    ISE
    0.22
    ly
    0.21
    äºİ
    0.19
     witness
    0.17
     Witness
    0.17
    ize
    0.17
     opinions
    0.17
    ease
    0.16
    Act Density 0.023%

    No Known Activations