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

    Neuronpedia

    INDEX
    Explanations

    terms related to sovereignty and integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phrine
    -0.79
    anguage
    -0.74
    bare
    -0.73
    ocation
    -0.72
    iking
    -0.69
    hower
    -0.66
    cale
    -0.66
    aces
    -0.65
    ites
    -0.64
    astical
    -0.64
    POSITIVE LOGITS
    rity
    0.89
     integrity
    0.82
     Integrity
    0.78
    imately
    0.69
    gil
    0.69
    amental
    0.68
    ively
    0.68
    rieved
    0.63
    ividual
    0.63
    Asset
    0.61
    Act Density 0.049%

    No Known Activations