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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles to follow

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Follow" related to social media or online interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    posing
    -0.75
    ukemia
    -0.71
    ãĤ¨ãĥ«
    -0.70
     wounding
    -0.68
    ãĥĨãĤ£
    -0.68
    pite
    -0.67
     Scotia
    -0.67
    ULT
    -0.65
     Dum
    -0.64
    cer
    -0.63
    POSITIVE LOGITS
     Follow
    1.25
    follow
    0.94
    ers
    0.87
    Follow
    0.84
    ership
    0.80
     Subscribe
    0.80
    edIn
    0.72
    LLOW
    0.72
    SHIP
    0.71
    cies
    0.70
    Act Density 0.006%

    No Known Activations