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

    Neuronpedia

    INDEX
    Explanations

    phrases that express hope or desire for outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rech
    -0.16
    arrow
    -0.16
    ves
    -0.15
    æ¡Ĥ
    -0.15
    .interfaces
    -0.15
     Harrison
    -0.14
    indir
    -0.14
    <>
    -0.14
    lla
    -0.14
    ongo
    -0.14
    POSITIVE LOGITS
    кÑĤа
    0.15
     Yen
    0.15
    neys
    0.15
     Reno
    0.14
    ãģ¾ãģŁ
    0.14
    OLS
    0.14
     Byron
    0.14
    omba
    0.14
    ivial
    0.14
     combin
    0.14
    Act Density 0.027%

    No Known Activations