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

    Neuronpedia

    INDEX
    Explanations

    instances of pairing or relationships between different entities

    oai_token-act-pair · gpt-3.5-turbo

    the term "other" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worth
    -0.75
    iah
    -0.75
    ardo
    -0.67
    haus
    -0.64
    istan
    -0.63
    ista
    -0.62
    omes
    -0.59
    kens
    -0.59
     ItemLevel
    -0.57
    iem
    -0.57
    POSITIVE LOGITS
     other
    2.98
    other
    2.18
     others
    2.14
     OTHER
    2.02
     Other
    1.83
    Other
    1.83
    Others
    1.55
     Others
    1.49
    OTHER
    1.46
     subsequent
    1.27
    Act Density 0.095%

    No Known Activations