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

    Neuronpedia

    INDEX
    Explanations

    words containing the root "col"

    oai_token-act-pair · gpt-3.5-turbo

    references to colors or terms related to color

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plug
    -0.76
    WARE
    -0.74
    wered
    -0.74
    ARP
    -0.69
    ELF
    -0.68
    visor
    -0.68
    natureconservancy
    -0.65
    CVE
    -0.65
    INST
    -0.64
     compr
    -0.63
    POSITIVE LOGITS
    onel
    1.07
    iseum
    1.05
    ossus
    1.01
    ossal
    0.94
    umbo
    0.92
    lections
    0.90
    oured
    0.89
    ombo
    0.88
    umn
    0.87
    icol
    0.87
    Act Density 0.011%

    No Known Activations