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

    Neuronpedia

    INDEX
    Explanations

    mentions of corporate entities or structures

    oai_token-act-pair · gpt-3.5-turbo

    references to corporate entities and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.93
    theless
    -0.86
    lihood
    -0.76
    lessly
    -0.74
    itudinal
    -0.72
    eful
    -0.72
    itives
    -0.72
    ï¸
    -0.71
    ebook
    -0.70
    mble
    -0.70
    POSITIVE LOGITS
     executives
    0.93
     sponsorship
    0.93
    orpor
    0.92
    porate
    0.91
     restructuring
    0.87
     espionage
    0.86
     conglomer
    0.85
     headquarters
    0.82
     corporations
    0.80
     corporation
    0.80
    Act Density 0.014%

    No Known Activations