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

    Neuronpedia

    INDEX
    Explanations

    terminology related to networks and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     centr
    -0.17
    thora
    -0.15
    thing
    -0.14
    ptest
    -0.14
    _redirected
    -0.14
    .Toolkit
    -0.14
    amt
    -0.14
     доÑģÑĤаÑĤ
    -0.14
    exampleInput
    -0.14
    gmt
    -0.14
    POSITIVE LOGITS
     offer
    0.25
     offers
    0.24
     requ
    0.22
     generally
    0.21
     tend
    0.20
     requires
    0.19
     advantages
    0.19
     tends
    0.19
     require
    0.19
     allows
    0.18
    Act Density 0.238%

    No Known Activations