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

    Neuronpedia

    INDEX
    Explanations

    words associated with complexity and nuance in expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Narr
    -0.16
    enville
    -0.16
    ernaut
    -0.15
     Barnett
    -0.15
    eric
    -0.14
    ongyang
    -0.14
     nIndex
    -0.14
    668
    -0.14
    žÃŃ
    -0.14
    bes
    -0.13
    POSITIVE LOGITS
    edo
    0.15
    wiÄħ
    0.15
    toi
    0.14
    Magn
    0.14
    Toe
    0.14
    Ðĭ
    0.14
    ómo
    0.14
    otate
    0.14
    agi
    0.14
    oes
    0.14
    Act Density 0.005%

    No Known Activations