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

    Neuronpedia

    INDEX
    Explanations

    words describing intrigue or compelling interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikers
    -0.18
    YST
    -0.17
    ovan
    -0.15
    avenport
    -0.15
    otate
    -0.15
    elize
    -0.15
    odox
    -0.15
    aleigh
    -0.15
    itore
    -0.14
    ç°
    -0.14
    POSITIVE LOGITS
    bul
    0.14
    rale
    0.14
     fasc
    0.14
    ritz
    0.14
     bul
    0.13
     glyc
    0.13
    und
    0.13
    ortion
    0.13
     undone
    0.13
    amera
    0.13
    Act Density 0.021%

    No Known Activations