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

    Neuronpedia

    INDEX
    Explanations

    concepts related to change and persistence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hid
    -0.15
     Laur
    -0.15
     Å
    -0.15
     Ñģеб
    -0.14
     Wilde
    -0.14
    ibold
    -0.13
     lad
    -0.13
    VB
    -0.13
     Farrell
    -0.13
    ยะ
    -0.13
    POSITIVE LOGITS
    jang
    0.19
    ucer
    0.16
    gang
    0.15
    usting
    0.15
    elow
    0.15
    å½ĵ
    0.14
    akis
    0.14
    tering
    0.14
    isEnabled
    0.14
    usher
    0.14
    Act Density 0.050%

    No Known Activations