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

    Neuronpedia

    INDEX
    Explanations

    words related to various states of being or conditions, such as moral or ethical qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibilit
    -0.17
    peria
    -0.17
    gne
    -0.15
    unden
    -0.14
    imd
    -0.14
    quette
    -0.14
    ÅĻÃŃm
    -0.14
    ViewState
    -0.14
    lessness
    -0.14
    IBILITY
    -0.14
    POSITIVE LOGITS
    ly
    1.20
    LY
    0.84
    ely
    0.81
    ily
    0.69
    ally
    0.68
    edly
    0.63
    ially
    0.63
    ley
    0.62
    mente
    0.62
    fully
    0.61
    Act Density 0.245%

    No Known Activations