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

    Neuronpedia

    INDEX
    Explanations

    phrases related to formal declarations or announcements

    oai_token-act-pair · gpt-3.5-turbo

    declarations of states or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eret
    -0.68
     hoops
    -0.68
    swick
    -0.65
     ups
    -0.64
     scanner
    -0.63
     doses
    -0.61
     revelations
    -0.61
     ramps
    -0.61
     intrig
    -0.61
     heels
    -0.60
    POSITIVE LOGITS
     allegiance
    0.84
    ocide
    0.78
    mberg
    0.74
     unfit
    0.74
    currency
    0.72
     loyalty
    0.70
    clusively
    0.70
    Flag
    0.69
    Ko
    0.69
     caliphate
    0.68
    Act Density 0.144%

    No Known Activations