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

    Neuronpedia

    INDEX
    Explanations

    phrases involving numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zs
    -0.16
    si
    -0.15
    aving
    -0.15
    ék
    -0.15
    ros
    -0.15
    624
    -0.14
    arel
    -0.14
     Preis
    -0.14
    893
    -0.14
    272
    -0.14
    POSITIVE LOGITS
    acional
    0.15
    deme
    0.15
    ahir
    0.14
    odox
    0.14
    asaki
    0.14
    umu
    0.14
     loss
    0.13
    TJ
    0.13
    addOn
    0.13
    iffs
    0.13
    Act Density 0.396%

    No Known Activations