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

    Neuronpedia

    INDEX
    Explanations

    references to original works of art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ings
    -0.16
    ess
    -0.15
    ethoven
    -0.15
    lej
    -0.15
    usal
    -0.14
    fen
    -0.14
    alfa
    -0.13
    ego
    -0.13
    INGS
    -0.13
    inger
    -0.13
    POSITIVE LOGITS
    ity
    0.44
    ITY
    0.26
    mente
    0.22
    ities
    0.21
    itty
    0.20
    y
    0.20
    idad
    0.19
     intent
    0.19
    /original
    0.18
     sin
    0.18
    Act Density 0.031%

    No Known Activations