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

    Neuronpedia

    INDEX
    Explanations

    comma-separated phrases

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or clauses indicating agreement or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -+
    -0.75
    igion
    -0.74
    arted
    -0.73
    èĢħ
    -0.71
    ende
    -0.70
    foreseen
    -0.69
    ighed
    -0.69
    minster
    -0.69
    folio
    -0.68
    mination
    -0.68
    POSITIVE LOGITS
     yes
    1.10
     sir
    1.07
     indeed
    1.03
     yeah
    1.02
     there
    0.98
     THERE
    0.91
     technically
    0.90
     it
    0.90
     please
    0.88
     seriously
    0.86
    Act Density 0.050%

    No Known Activations