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

    Neuronpedia

    INDEX
    Explanations

    names of prominent political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grove
    -0.16
    anga
    -0.15
     Blond
    -0.14
    åde
    -0.14
    aç
    -0.14
    ackle
    -0.14
    IFEST
    -0.13
    Å¡en
    -0.13
     dna
    -0.13
    rove
    -0.13
    POSITIVE LOGITS
    cts
    0.15
     blind
    0.15
    оÑģÑĮ
    0.14
    ALI
    0.14
    ceph
    0.14
    extr
    0.13
    assic
    0.13
     Tob
    0.13
    adece
    0.13
    ÑĪли
    0.13
    Act Density 0.015%

    No Known Activations