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

    Neuronpedia

    INDEX
    Explanations

    words related to political figures and activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political contexts and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alto
    -0.61
    flush
    -0.59
    stadt
    -0.59
    leasing
    -0.58
    alone
    -0.56
     Weber
    -0.56
    tails
    -0.55
    Mist
    -0.55
    Desktop
    -0.54
    door
    -0.54
    POSITIVE LOGITS
     correctness
    0.75
     speeches
    0.69
    ndum
    0.67
    clinton
    0.65
     pamph
    0.63
     slogans
    0.61
    aroo
    0.61
    xual
    0.61
    EStream
    0.60
     hostage
    0.60
    Act Density 0.600%

    No Known Activations