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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional or evaluative states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¸
    -0.16
    aso
    -0.15
    te
    -0.14
    ripple
    -0.13
    ÛĮاÙĨ
    -0.13
    enco
    -0.13
    ramids
    -0.13
    kaz
    -0.13
     Cone
    -0.13
     Huffman
    -0.13
    POSITIVE LOGITS
    abox
    0.18
    hiba
    0.17
    ÑĢоÑģÑĤо
    0.15
    -cons
    0.14
    lector
    0.14
    -д
    0.14
    borg
    0.13
    wide
    0.13
    .drawRect
    0.13
    edback
    0.13
    Act Density 0.085%

    No Known Activations