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

    Neuronpedia

    INDEX
    Explanations

    phrases related to corporations

    oai_token-act-pair · gpt-3.5-turbo

    the prefix or standalone word "cor"

    oai_token-act-pair · gpt-4-turbo

    references to corporate entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.82
    HAHAHAHA
    -0.78
     Hits
    -0.72
    staking
    -0.72
    éĹĺ
    -0.70
     Finder
    -0.69
    HAHA
    -0.68
     Thrust
    -0.67
    UME
    -0.66
     ACTIONS
    -0.66
    POSITIVE LOGITS
    porate
    1.39
    ruption
    1.19
    ridor
    1.16
    poral
    1.07
    rupted
    1.04
    por
    1.03
    rupt
    1.02
    rection
    1.00
    byn
    0.97
    rigan
    0.97
    Act Density 0.009%

    No Known Activations