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

    Neuronpedia

    INDEX
    Explanations

    references to experiences or expressions of appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pag
    -0.14
    -↵
    -0.14
    -↵↵
    -0.14
     lim
    -0.13
     Bond
    -0.13
     APK
    -0.13
     ↵
    -0.13
    530
    -0.12
    -0.12
     Fortune
    -0.12
    POSITIVE LOGITS
    erece
    0.17
    esiz
    0.16
    akis
    0.16
    ardu
    0.15
    ÃŃme
    0.15
    rve
    0.14
     nuest
    0.14
    861
    0.14
    oose
    0.14
    ONGL
    0.14
    Act Density 0.662%

    No Known Activations