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

    Neuronpedia

    INDEX
    Explanations

    sequences indicating a multi-step process or a specific type of system

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of systems or structures involving multiple paths or layers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.88
    wolves
    -0.76
     Rena
    -0.67
    natureconservancy
    -0.65
    apist
    -0.64
    zynski
    -0.64
    uca
    -0.64
    uden
    -0.64
    isco
    -0.63
    polit
    -0.63
    POSITIVE LOGITS
     affair
    0.86
    ounce
    0.80
     combo
    0.76
     striped
    0.75
     configurations
    0.74
    ĪĴ
    0.70
    clusive
    0.69
    clusively
    0.69
    llor
    0.67
     jewel
    0.66
    Act Density 0.103%

    No Known Activations