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

    Neuronpedia

    INDEX
    Explanations

    references to specific documents or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vere
    -0.16
    lycer
    -0.15
    aine
    -0.14
     é©
    -0.14
    787
    -0.14
    obil
    -0.14
    kart
    -0.14
    iete
    -0.13
    lier
    -0.13
    åį·
    -0.13
    POSITIVE LOGITS
    raki
    0.16
    uppe
    0.16
    unft
    0.15
    Dlg
    0.15
    holes
    0.14
    oren
    0.14
    allon
    0.14
     داÙħ
    0.14
    pora
    0.14
    ouv
    0.13
    Act Density 0.025%

    No Known Activations