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

    Neuronpedia

    INDEX
    Explanations

    mentions of social media platforms and usernames

    oai_token-act-pair · gpt-3.5-turbo

    specific usernames or identities associated with social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confir
    -0.66
    rals
    -0.65
    ãĥł
    -0.63
    arsh
    -0.62
    robe
    -0.61
    acio
    -0.60
     srfAttach
    -0.60
    ousands
    -0.59
    lando
    -0.59
    ãĥ´
    -0.59
    POSITIVE LOGITS
    PLIED
    0.90
    liest
    0.75
     Certified
    0.74
     incarn
    0.74
    actly
    0.73
     certified
    0.71
     equivalent
    0.70
     accredited
    0.68
     anyway
    0.68
     Mecca
    0.66
    Act Density 0.982%

    No Known Activations