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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political or financial backing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to entities or actions that are supported by a state or government

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asonable
    -0.71
    itta
    -0.70
     SERV
    -0.68
     Harbor
    -0.67
     Hazard
    -0.67
     combust
    -0.66
     PERSON
    -0.66
     scratch
    -0.64
    istics
    -0.63
     Colo
    -0.63
    POSITIVE LOGITS
    backed
    0.90
    interstitial
    0.88
    ItemTracker
    0.86
    etheless
    0.83
    cham
    0.77
    terday
    0.75
    ragon
    0.73
    axter
    0.72
    jriwal
    0.72
     facilit
    0.70
    Act Density 0.031%

    No Known Activations