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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential conflicts of interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    off
    -0.17
    apa
    -0.16
    ichen
    -0.15
    اصÙĦÙĩ
    -0.14
    aved
    -0.14
    iline
    -0.14
    _throw
    -0.14
    æĹıèĩªæ²»
    -0.14
    ovsky
    -0.14
    cka
    -0.14
    POSITIVE LOGITS
     interest
    0.45
     Interest
    0.42
    -interest
    0.37
    Interest
    0.36
    interest
    0.36
    _interest
    0.32
     interests
    0.30
     interes
    0.28
     инÑĤеÑĢеÑģ
    0.26
     interesse
    0.25
    Act Density 0.003%

    No Known Activations