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

    Neuronpedia

    INDEX
    Explanations

    the word "share" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to shares or stakes in a financial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rohing
    -0.70
    herty
    -0.64
    lectic
    -0.61
    ensen
    -0.60
    letes
    -0.58
    istically
    -0.58
     trance
    -0.58
    lete
    -0.57
     fusion
    -0.57
     fatig
    -0.57
    POSITIVE LOGITS
    holding
    1.39
    holder
    1.36
    cro
    1.25
    holders
    1.25
    hold
    1.11
    owners
    1.02
    fair
    0.94
    ership
    0.94
    hare
    0.93
    DAQ
    0.91
    Act Density 0.045%

    No Known Activations