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

    Neuronpedia

    INDEX
    Explanations

    key terms related to climate news and descriptions of physical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to environmental topics and urban settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.79
    ãĤ¤ãĥĪ
    -0.78
    itiveness
    -0.78
    apest
    -0.77
    acci
    -0.76
    accompan
    -0.75
    iasco
    -0.73
    bitious
    -0.71
    yip
    -0.70
    quished
    -0.69
    POSITIVE LOGITS
    ĸļ
    0.71
     wedge
    0.70
     comfort
    0.66
     balcon
    0.64
    hyde
    0.63
    ifice
    0.62
     canyon
    0.62
     encl
    0.60
     fault
    0.60
    clave
    0.60
    Act Density 0.326%

    No Known Activations