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

    Neuronpedia

    INDEX
    Explanations

    terms related to corporations or companies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "corp" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.75
    TPS
    -0.70
     Hits
    -0.70
     Finder
    -0.68
    HAHAHAHA
    -0.66
    éĹĺ
    -0.66
    CRIP
    -0.66
     aloud
    -0.64
    STER
    -0.64
    HUD
    -0.63
    POSITIVE LOGITS
    porate
    1.45
    ruption
    1.27
    poral
    1.23
    ridor
    1.23
    rupted
    1.22
    rection
    1.18
    rupt
    1.16
    respond
    1.14
    por
    1.10
    pse
    1.09
    Act Density 0.011%

    No Known Activations