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

    Neuronpedia

    INDEX
    Explanations

    phrases that express definition or assertion of identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thon
    -0.18
    bose
    -0.17
    undy
    -0.17
    ully
    -0.17
    ött
    -0.16
    ical
    -0.15
    th
    -0.15
    ndl
    -0.15
    etas
    -0.15
    age
    -0.15
    POSITIVE LOGITS
    ally
    0.18
     phá»ij
    0.16
    inea
    0.14
    utive
    0.14
    Ưá»
    0.14
    .gameserver
    0.13
    ialect
    0.13
    atsu
    0.13
    amt
    0.13
     crown
    0.13
    Act Density 0.020%

    No Known Activations