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

    Neuronpedia

    INDEX
    Explanations

    sentences describing relationships or interactions between different entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of relationships between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Discuss
    -0.84
    stocks
    -0.76
    ï¸
    -0.74
     Citation
    -0.73
    notation
    -0.71
    ftime
    -0.71
    notations
    -0.70
    spir
    -0.68
    oren
    -0.67
    details
    -0.67
    POSITIVE LOGITS
     its
    0.80
     ours
    0.77
     theirs
    0.75
     the
    0.71
     those
    0.68
     their
    0.66
     vanquished
    0.64
     his
    0.63
     Nazis
    0.62
    mbuds
    0.61
    Act Density 0.111%

    No Known Activations