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

    Neuronpedia

    INDEX
    Explanations

    the word "Ent" followed by specific numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Ent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.82
    FUL
    -0.72
    ¨
    -0.67
     Archangel
    -0.65
    phrine
    -0.65
    utral
    -0.64
    utics
    -0.64
     sterling
    -0.64
     Jenner
    -0.63
    BILITY
    -0.63
    POSITIVE LOGITS
    ropy
    1.09
    inct
    1.03
    oyer
    0.96
     Ent
    0.95
    raction
    0.95
    itle
    0.94
    rance
    0.93
    itled
    0.91
    rants
    0.89
    ree
    0.88
    Act Density 0.007%

    No Known Activations