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

    Neuronpedia

    INDEX
    Explanations

    mention of government entities or official institutions

    oai_token-act-pair · gpt-3.5-turbo

    instances of government entities or mentions of governmental actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     imaginable
    -0.69
    inct
    -0.68
     fantasies
    -0.65
    lif
    -0.65
     overd
    -0.65
    plings
    -0.64
    bye
    -0.64
    stones
    -0.63
     transformations
    -0.62
     enchant
    -0.62
    POSITIVE LOGITS
     headquartered
    1.02
     chaired
    0.85
     meanwhile
    0.85
    Department
    0.82
    ItemTracker
    0.79
     Colleges
    0.78
     judiciary
    0.77
     citing
    0.76
     aided
    0.76
     which
    0.75
    Act Density 0.287%

    No Known Activations