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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing preferences or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern and emotional support within interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.93
    ãĤ´ãĥ³
    -0.87
    ¥ŀ
    -0.84
    ortium
    -0.81
    *:
    -0.78
    Indeed
    -0.75
    âĦ¢:
    -0.74
    surprisingly
    -0.73
    UGC
    -0.72
    éŃĶ
    -0.72
    POSITIVE LOGITS
    ,'"
    1.40
     âĢ¦"
    1.35
    .")
    1.28
    .'"
    1.28
     ..."
    1.23
    ?'"
    1.22
    ',"
    1.20
    !'"
    1.14
    ),"
    1.14
    ,"
    1.13
    Act Density 0.917%

    No Known Activations