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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated vowel characters and exaggerated expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏģÏį
    -0.15
    atrix
    -0.15
     Http
    -0.15
     MP
    -0.15
     Mp
    -0.15
    ultan
    -0.14
    MP
    -0.14
    aru
    -0.14
    oren
    -0.14
    amus
    -0.14
    POSITIVE LOGITS
    ãĥ³ãĥĦ
    0.16
    ertz
    0.16
    raman
    0.15
    .synthetic
    0.15
    mma
    0.14
    asions
    0.14
    ì°¬
    0.14
    ADS
    0.14
    agnet
    0.14
    umbed
    0.14
    Act Density 0.012%

    No Known Activations