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

    Neuronpedia

    INDEX
    Explanations

    hashtags used on social media posts

    oai_token-act-pair · gpt-3.5-turbo

    hashtags in social media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -+-+
    -0.71
    =-=-
    -0.70
     concede
    -0.69
     oun
    -0.68
     quir
    -0.65
    avorite
    -0.65
     previews
    -0.63
    ãĤ¨
    -0.63
    =-=-=-=-
    -0.60
    Ģ
    -0.60
    POSITIVE LOGITS
    cdn
    0.98
    amaz
    0.93
    realDonaldTrump
    0.89
    selves
    0.86
    twitter
    0.81
    holiday
    0.81
    define
    0.80
    sov
    0.79
    heid
    0.79
    self
    0.79
    Act Density 0.031%

    No Known Activations