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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to containing, housing, or supporting objects or entities

    oai_token-act-pair · gpt-3.5-turbo

    words related to capacity or support for various structures and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wrong
    -0.72
    externalActionCode
    -0.66
     Underground
    -0.64
    binary
    -0.64
    isan
    -0.62
    isf
    -0.61
    ritz
    -0.61
    displayText
    -0.61
    oshenko
    -0.61
    imet
    -0.60
    POSITIVE LOGITS
     tons
    0.87
     plenty
    0.74
     loads
    0.72
     considerable
    0.69
    ãĥīãĥ©ãĤ´ãĥ³
    0.67
     millions
    0.65
    nia
    0.64
     some
    0.64
     hosting
    0.64
     riches
    0.64
    Act Density 0.269%

    No Known Activations