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

    Neuronpedia

    INDEX
    Explanations

    words related to authority, control, and power dynamics

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and coordinating phrases indicating actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pony
    -0.72
     Flying
    -0.71
     Shots
    -0.68
    ETS
    -0.67
     Jets
    -0.66
     Hands
    -0.66
     Baseball
    -0.66
    ardi
    -0.65
     Lines
    -0.65
     Tok
    -0.63
    POSITIVE LOGITS
     degrade
    1.12
    rogen
    1.07
    igmat
    1.05
     amplify
    1.05
     distort
    1.04
     humili
    1.04
    rogens
    1.02
     eliminate
    1.02
     discredit
    0.99
     automate
    0.98
    Act Density 0.141%

    No Known Activations