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

    Neuronpedia

    INDEX
    Explanations

    phrases related to large numbers and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to significant entities or concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reply
    -0.63
     Rasmussen
    -0.63
    Published
    -0.62
     FTA
    -0.59
    database
    -0.58
     Neighbor
    -0.56
     Posted
    -0.56
     âĢİ
    -0.56
     ASA
    -0.56
    ioxide
    -0.55
    POSITIVE LOGITS
     versa
    0.90
     ones
    0.85
     themselves
    0.76
     thereof
    0.76
    ally
    0.68
     itself
    0.67
     ourselves
    0.62
     equivalents
    0.61
     counterparts
    0.60
     penn
    0.59
    Act Density 0.836%

    No Known Activations