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

    Neuronpedia

    INDEX
    Explanations

    words related to academic qualifications and formal titles

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to causality and fundamental status in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itars
    -0.77
    builders
    -0.69
    rooms
    -0.69
    urches
    -0.64
     Rooms
    -0.64
    urrencies
    -0.63
     Pets
    -0.62
    ouls
    -0.62
    nces
    -0.61
    eworks
    -0.61
    POSITIVE LOGITS
     standpoint
    0.86
     inhibitor
    0.75
     perspective
    0.74
     endorsement
    0.69
    elist
    0.67
     indicator
    0.66
    ussian
    0.65
     approximation
    0.65
     bucket
    0.64
     diploma
    0.64
    Act Density 1.014%

    No Known Activations