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

    Neuronpedia

    INDEX
    Explanations

    structured citations and references typically found in academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olumn
    -0.16
     chr
    -0.15
    uds
    -0.14
    acob
    -0.14
     ~=
    -0.14
     paso
    -0.14
    ivor
    -0.14
    ovol
    -0.14
    enticate
    -0.14
    aku
    -0.13
    POSITIVE LOGITS
     Sailor
    0.17
     Joker
    0.17
    ACS
    0.16
     Fransa
    0.16
    ITHER
    0.16
     Aws
    0.16
     Fade
    0.15
    iores
    0.15
     Betting
    0.15
    jec
    0.15
    Act Density 0.021%

    No Known Activations