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

    Neuronpedia

    INDEX
    Explanations

    references to publications or press releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uses
    -0.15
    ournée
    -0.15
     mate
    -0.14
    atra
    -0.14
     Bail
    -0.14
    rani
    -0.14
    éłŃ
    -0.14
    aptor
    -0.14
    acking
    -0.14
    etails
    -0.13
    POSITIVE LOGITS
    hausen
    0.20
    ë¶ģ
    0.15
    oulos
    0.14
     wonder
    0.14
    lassen
    0.14
    crement
    0.14
     Hitch
    0.14
    onas
    0.14
    .opendaylight
    0.14
    poÄįet
    0.14
    Act Density 0.038%

    No Known Activations