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

    Neuronpedia

    INDEX
    Explanations

    terms related to neon lights and glowing objects

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "neon" and similar visually vibrant terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.91
    atchewan
    -0.82
    CVE
    -0.80
    iyah
    -0.76
    GRE
    -0.74
    tta
    -0.74
    BOOK
    -0.74
    gerald
    -0.72
    enance
    -0.71
    ":[{"
    -0.70
    POSITIVE LOGITS
    atal
    1.19
     neon
    0.75
    cephal
    0.74
    ulously
    0.73
    etheless
    0.72
     squid
    0.72
    atur
    0.72
     mascul
    0.71
    aval
    0.71
    ocon
    0.70
    Act Density 0.018%

    No Known Activations