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

    Neuronpedia

    INDEX
    Explanations

    words related to city infrastructure and reporting issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ARP
    -0.68
    VIS
    -0.63
    backer
    -0.62
    cius
    -0.59
     Aires
    -0.57
    ELF
    -0.56
    ARK
    -0.55
    HT
    -0.54
    CVE
    -0.53
    nington
    -0.53
    POSITIVE LOGITS
    icz
    0.75
    lections
    0.74
    mson
    0.74
    oured
    0.74
    ortex
    0.71
    lected
    0.70
    ouring
    0.70
    iflower
    0.66
    umn
    0.64
    osph
    0.62
    Act Density 7.037%

    No Known Activations