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

    Neuronpedia

    INDEX
    Explanations

    references to global entities and activities involving collaboration or widespread influence

    oai_token-act-pair · gpt-3.5-turbo

    references to worldwide collaboration and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     boun
    -0.66
    /+
    -0.66
     correction
    -0.63
    =/
    -0.63
     bounces
    -0.63
     Resurrection
    -0.61
     Ends
    -0.60
     zo
    -0.60
    ipop
    -0.60
     {*
    -0.60
    POSITIVE LOGITS
     alike
    1.15
     collectively
    1.13
     converge
    0.97
     conver
    0.95
     respectively
    0.93
     attest
    0.89
     clam
    0.87
     united
    0.85
     unanimously
    0.85
    together
    0.81
    Act Density 0.490%

    No Known Activations