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

    Neuronpedia

    INDEX
    Explanations

    references to faux or auxiliary concepts and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berger
    -0.17
    iesel
    -0.17
    .pag
    -0.17
    jez
    -0.15
    benh
    -0.15
    jem
    -0.15
    ammer
    -0.15
    riet
    -0.14
    rist
    -0.14
    бÑĭ
    -0.14
    POSITIVE LOGITS
    ledge
    0.16
     dob
    0.15
    ãĤ¢ãĥ¼
    0.15
    ģ
    0.14
     Bloss
    0.13
     tail
    0.13
    ère
    0.13
     çĬ
    0.13
    AndWait
    0.13
    istory
    0.13
    Act Density 0.008%

    No Known Activations