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

    Neuronpedia

    INDEX
    Explanations

    social media actions or commands

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to social media engagement, particularly the concept of "liking."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.98
    inas
    -0.83
    ennes
    -0.75
    ictional
    -0.67
    endiary
    -0.67
    restrial
    -0.67
    cill
    -0.67
    rete
    -0.66
    ë
    -0.66
    Euro
    -0.64
    POSITIVE LOGITS
    lihood
    2.08
    liest
    1.15
    lier
    1.06
    minded
    0.89
    liness
    0.87
     minded
    0.84
    ably
    0.76
     wildfire
    0.76
    ability
    0.73
    able
    0.68
    Act Density 0.049%

    No Known Activations