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

    Neuronpedia

    INDEX
    Explanations

    mentions of social media platforms like Twitter and Facebook

    oai_token-act-pair · gpt-3.5-turbo

    connections to social media platforms, particularly Twitter and Facebook

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enh
    -0.68
     optics
    -0.61
     fatig
    -0.59
     rounds
    -0.57
    awan
    -0.56
     coercion
    -0.56
     electrodes
    -0.56
     consequences
    -0.54
     Kis
    -0.54
     necessity
    -0.54
    POSITIVE LOGITS
    ombat
    0.92
    ONSORED
    0.91
    76561
    0.83
    ascript
    0.82
    Interstitial
    0.77
    orthern
    0.75
    SPONSORED
    0.75
    psc
    0.74
    ··
    0.72
    ï¸ı
    0.71
    Act Density 0.145%

    No Known Activations