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

    Neuronpedia

    INDEX
    Explanations

    third-person pronouns indicating a person or group before an action that affects them

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating specific individuals and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Consortium
    -0.76
     Canaver
    -0.66
     Resistance
    -0.65
     Premiership
    -0.64
     Speedway
    -0.64
     Federation
    -0.63
    etheless
    -0.63
     understatement
    -0.62
     Electrical
    -0.62
     Reloaded
    -0.61
    POSITIVE LOGITS
    've
    1.04
     began
    0.90
     arrived
    0.90
     started
    0.89
    're
    0.87
     commenced
    0.86
     own
    0.84
    'd
    0.84
     became
    0.83
     embarked
    0.80
    Act Density 0.246%

    No Known Activations