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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing varying degrees of quality or descriptive characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chg
    -0.19
    utter
    -0.16
    remely
    -0.16
    riz
    -0.14
    еÑĢÑĪ
    -0.14
    uat
    -0.14
    nt
    -0.14
    imizer
    -0.14
    utura
    -0.14
    heet
    -0.13
    POSITIVE LOGITS
    -sort
    0.24
     like
    0.23
     Like
    0.19
    -ÑĤаки
    0.17
     LIKE
    0.17
    thing
    0.17
    Like
    0.16
    /s
    0.15
    awks
    0.15
     tw
    0.15
    Act Density 0.022%

    No Known Activations