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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social media engagement such as "follow us"

    oai_token-act-pair · gpt-3.5-turbo

    commands and suggestions related to following on social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inese
    -0.72
    pter
    -0.70
    laugh
    -0.68
    cer
    -0.66
    hya
    -0.64
    ikuman
    -0.64
     wounding
    -0.64
    urrection
    -0.64
    aez
    -0.64
    cin
    -0.64
    POSITIVE LOGITS
     closely
    1.07
     along
    1.03
     directions
    0.99
     instructions
    0.97
     suit
    0.83
    Sym
    0.76
     Follow
    0.74
    pend
    0.71
     clues
    0.71
     developments
    0.70
    Act Density 0.033%

    No Known Activations