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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative events, such as deaths and arrests

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of death or destruction and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mie
    -0.69
    issance
    -0.69
    yip
    -0.67
    erity
    -0.66
    anny
    -0.60
     00
    -0.59
     Tire
    -0.59
     ¯
    -0.58
    chief
    -0.56
    roo
    -0.56
    POSITIVE LOGITS
     themselves
    0.97
     outright
    0.86
     respectively
    0.81
     leases
    0.77
     apiece
    0.77
    onyms
    0.74
    osponsors
    0.74
     individually
    0.73
     voluntarily
    0.73
     redund
    0.72
    Act Density 0.483%

    No Known Activations