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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles for different people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media and interpersonal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forced
    -0.58
     wounding
    -0.55
    etheless
    -0.55
    venge
    -0.54
    erous
    -0.54
    uple
    -0.54
    etime
    -0.53
     manif
    -0.52
    ģĸ
    -0.52
     sped
    -0.52
    POSITIVE LOGITS
     @
    1.11
     (@
    0.95
     on
    0.84
    Dispatch
    0.83
     twitter
    0.72
    edin
    0.70
     updates
    0.70
    iannopoulos
    0.69
     Twitter
    0.68
     hasht
    0.68
    Act Density 0.046%

    No Known Activations