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

    Neuronpedia

    INDEX
    Explanations

    words related to personification and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lev
    -0.18
     Lev
    -0.17
    ron
    -0.16
    rons
    -0.16
    eron
    -0.14
    lev
    -0.14
    Prec
    -0.14
     Marina
    -0.14
    oons
    -0.14
    agal
    -0.14
    POSITIVE LOGITS
     Lowe
    0.15
     Scale
    0.15
     Starr
    0.15
    emplo
    0.14
    -Ta
    0.14
    977
    0.14
    Scale
    0.13
    éĢĢ
    0.13
    abin
    0.13
    zem
    0.13
    Act Density 0.014%

    No Known Activations