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

    Neuronpedia

    INDEX
    Explanations

    references to teaching, sharing knowledge, and supporting others' development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idth
    -0.17
    ikh
    -0.16
    okus
    -0.15
     Saud
    -0.15
    ãĥ©ãĤ¹
    -0.15
    RET
    -0.14
    æģ¯
    -0.14
    wind
    -0.14
    ieux
    -0.14
    udent
    -0.14
    POSITIVE LOGITS
     Legend
    0.15
     Deck
    0.14
    ologies
    0.14
     spin
    0.14
     Logical
    0.14
     Claud
    0.14
    ordo
    0.14
    806
    0.14
     tent
    0.13
     Century
    0.13
    Act Density 0.406%

    No Known Activations