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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the establishment of organizations, systems, or programs

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the establishment or creation of entities, structures, or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    axe
    -0.79
    fully
    -0.75
    bits
    -0.72
    jee
    -0.72
    matter
    -0.70
     untreated
    -0.70
    wright
    -0.70
    mong
    -0.70
    wash
    -0.68
    luent
    -0.68
    POSITIVE LOGITS
     precedent
    0.82
     perimeter
    0.78
     reserve
    0.76
     rapport
    0.75
     sanctuary
    0.75
     Sanctuary
    0.74
     Headquarters
    0.74
     permanent
    0.70
     headquarters
    0.69
     embassy
    0.69
    Act Density 0.212%

    No Known Activations