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

    Neuronpedia

    INDEX
    Explanations

    phrases related to improvement and efficiency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amac
    -0.16
     gall
    -0.15
     duty
    -0.15
    одав
    -0.15
    zar
    -0.15
     majors
    -0.14
    Dispatch
    -0.14
    lingen
    -0.14
    pur
    -0.14
     closely
    -0.14
    POSITIVE LOGITS
     Academ
    0.15
    /ts
    0.14
     onMouse
    0.14
    è¡Ľ
    0.14
    ercul
    0.14
    eselect
    0.13
    itr
    0.13
    rift
    0.13
    rik
    0.13
     Kür
    0.13
    Act Density 0.260%

    No Known Activations