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

    Neuronpedia

    INDEX
    Explanations

    mentions of geographical locations and adjectives related to nationality

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nationality or geographical origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idden
    -0.72
    atown
    -0.71
    fo
    -0.69
    okin
    -0.69
    ushima
    -0.69
    usters
    -0.63
    imag
    -0.63
    odes
    -0.62
    omed
    -0.62
     calibration
    -0.61
    POSITIVE LOGITS
     Liam
    0.82
     Joey
    0.80
     Shaun
    0.77
     Jeremiah
    0.77
     Damon
    0.75
     Colin
    0.74
     Ezra
    0.74
     winger
    0.74
     Reggie
    0.73
     Ezekiel
    0.73
    Act Density 0.109%

    No Known Activations