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

    Neuronpedia

    INDEX
    Explanations

    phrases related to appreciation and personal growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rete
    -0.16
    hart
    -0.15
    apel
    -0.15
    irates
    -0.15
    hra
    -0.15
    enthal
    -0.15
    ulet
    -0.14
    raž
    -0.14
     slik
    -0.14
    adla
    -0.14
    POSITIVE LOGITS
    éré
    0.14
     scor
    0.14
     Ne
    0.14
     toward
    0.14
    LayoutManager
    0.14
    alborg
    0.14
    *)((
    0.14
    Streamer
    0.13
    445
    0.13
     Griffith
    0.13
    Act Density 0.002%

    No Known Activations