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

    Neuronpedia

    INDEX
    Explanations

    verbs related to discussing or considering topics and possibilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to issues being irrelevant or inconsequential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orr
    -0.84
    uve
    -0.82
    atton
    -0.77
    ibaba
    -0.77
    ieve
    -0.72
    urses
    -0.70
    utics
    -0.70
    ibr
    -0.69
    ournals
    -0.69
    aucas
    -0.68
    POSITIVE LOGITS
     moot
    1.00
    yrinth
    0.82
    founded
    0.82
    spot
    0.76
    enegger
    0.75
    IOR
    0.75
    sonian
    0.71
    jet
    0.70
    pton
    0.70
     debated
    0.69
    Act Density 0.024%

    No Known Activations