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

    Neuronpedia

    INDEX
    Explanations

    words related to rumors or gossip

    oai_token-act-pair · gpt-3.5-turbo

    references to "rum" or related terms within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canadians
    -0.72
     CPC
    -0.70
     ethic
    -0.67
     impunity
    -0.65
     Australians
    -0.63
     Padres
    -0.60
     human
    -0.60
    hiro
    -0.60
     subp
    -0.59
     AAP
    -0.59
    POSITIVE LOGITS
    rum
    1.28
    ming
    0.98
    atis
    0.92
    unity
    0.88
    ble
    0.87
    mers
    0.84
    rums
    0.82
    mond
    0.81
    BLE
    0.81
    bug
    0.79
    Act Density 0.006%

    No Known Activations