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

    Neuronpedia

    INDEX
    Explanations

    words related to names or titles that end in "mon"

    oai_token-act-pair · gpt-3.5-turbo

    words related to ceremonial or ritualistic occasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Norn
    -0.73
    FUL
    -0.64
     Paste
    -0.64
    EMP
    -0.64
    NRS
    -0.64
    unta
    -0.61
    ENG
    -0.61
    ACTED
    -0.60
    RED
    -0.59
     Prescott
    -0.59
    POSITIVE LOGITS
    strous
    1.12
    itored
    1.10
    etary
    1.06
    ial
    1.03
    ials
    0.96
    uclear
    0.92
    ths
    0.92
    astery
    0.91
    iac
    0.91
    stros
    0.87
    Act Density 0.025%

    No Known Activations