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

    Neuronpedia

    INDEX
    Explanations

    phrases related to things that prevent or allow progress or movement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express ongoing constraints or factors that maintain certain situations or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vised
    -0.77
     consulted
    -0.66
    morph
    -0.66
    eal
    -0.65
    qua
    -0.64
    TPPStreamerBot
    -0.63
     ende
    -0.63
    ãĥ¯ãĥ³
    -0.62
    fax
    -0.62
    idelines
    -0.62
    POSITIVE LOGITS
     us
    1.26
     them
    1.09
     people
    1.00
     employers
    0.97
     users
    0.93
     consumers
    0.90
     individuals
    0.88
     me
    0.88
     travelers
    0.86
     perpetrators
    0.86
    Act Density 0.189%

    No Known Activations