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

    Neuronpedia

    INDEX
    Explanations

    words related to improvement or enhancement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to improvement and enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mortal
    -0.60
     Apostles
    -0.60
     Warriors
    -0.58
     Frozen
    -0.58
     Apostle
    -0.57
     Alive
    -0.57
    fing
    -0.54
    aries
    -0.53
     Cro
    -0.53
    death
    -0.53
    POSITIVE LOGITS
     misunder
    0.90
    ments
    0.90
    eston
    0.86
    oshop
    0.85
    uate
    0.83
    urate
    0.79
    itial
    0.74
     tremend
    0.73
     deepen
    0.72
    uates
    0.72
    Act Density 0.067%

    No Known Activations