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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest reasoning or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odem
    -0.15
     Rou
    -0.15
    ffb
    -0.15
    xee
    -0.15
    pix
    -0.14
     Dent
    -0.14
     éc
    -0.14
    umer
    -0.14
    ROUT
    -0.13
     familiar
    -0.13
    POSITIVE LOGITS
    adol
    0.15
    нок
    0.14
    horia
    0.14
     ساز
    0.14
    @qq
    0.14
    æ¦
    0.13
    ëł´
    0.13
    FIT
    0.13
    alic
    0.13
    Inflater
    0.13
    Act Density 0.244%

    No Known Activations