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

    Neuronpedia

    INDEX
    Explanations

    terms related to expertise and expert roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quist
    -0.17
    èĸ
    -0.16
    acher
    -0.16
    lian
    -0.15
    uments
    -0.15
    antics
    -0.15
    ffect
    -0.15
    cloth
    -0.15
    ĥĿ
    -0.15
    agra
    -0.15
    POSITIVE LOGITS
    ise
    0.39
    ises
    0.30
    ly
    0.26
    ISE
    0.25
    ize
    0.24
     opinions
    0.21
     opinion
    0.20
    ised
    0.20
     witness
    0.19
    -level
    0.19
    Act Density 0.026%

    No Known Activations