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

    Neuronpedia

    INDEX
    Explanations

    phrases focusing on observation or emotion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombs
    -0.66
    âĹ¼
    -0.64
    rolet
    -0.63
    Enlarge
    -0.63
    Going
    -0.63
    Site
    -0.63
    ruct
    -0.62
    REE
    -0.62
    riz
    -0.61
    Gender
    -0.61
    POSITIVE LOGITS
    phy
    1.10
     opposed
    0.97
    piring
    0.96
    pires
    0.96
     well
    0.93
    pired
    0.87
     evidenced
    0.81
    ides
    0.81
    phalt
    0.80
     soon
    0.79
    Act Density 0.170%

    No Known Activations