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

    Neuronpedia

    INDEX
    Explanations

    phrases related to clarity and transparency in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasi
    -0.15
    etr
    -0.14
    view
    -0.14
    нин
    -0.14
    icros
    -0.14
    è°ĥ
    -0.14
    -rad
    -0.13
     поглÑıд
    -0.13
    eping
    -0.13
     yorum
    -0.13
    POSITIVE LOGITS
     spell
    0.44
     spells
    0.39
     Spell
    0.38
    spell
    0.38
     SPELL
    0.35
    Spell
    0.34
     spelling
    0.32
     Spells
    0.32
     clearly
    0.31
     state
    0.28
    Act Density 0.317%

    No Known Activations