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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating warnings or cautionary sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sogar
    -0.16
    adla
    -0.15
    imbus
    -0.14
     zwar
    -0.14
    ITO
    -0.14
    really
    -0.14
     nawet
    -0.14
    adlo
    -0.14
    zp
    -0.14
    .ta
    -0.14
    POSITIVE LOGITS
     nor
    0.33
     Nor
    0.28
    Nor
    0.26
    nor
    0.24
     anymore
    0.21
     occasionally
    0.19
     NOR
    0.17
     sondern
    0.16
     Norris
    0.16
     occasional
    0.16
    Act Density 0.137%

    No Known Activations