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

    Neuronpedia

    INDEX
    Explanations

    concepts related to complexity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikip
    -0.18
    lit
    -0.16
     witness
    -0.16
    fir
    -0.16
    iki
    -0.16
    askan
    -0.15
    baz
    -0.15
    etry
    -0.15
    born
    -0.15
    duk
    -0.15
    POSITIVE LOGITS
     enough
    0.16
    sterol
    0.16
    xes
    0.15
    ÑīÑĸ
    0.15
    ene
    0.14
     complex
    0.14
    evin
    0.14
    endo
    0.14
    олÑĸ
    0.14
    hdr
    0.14
    Act Density 0.051%

    No Known Activations