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

    Neuronpedia

    INDEX
    Explanations

    keywords related to relocation or moving from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    terms related to moving or changing locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.85
    bara
    -0.75
    reme
    -0.71
    chest
    -0.70
    chain
    -0.69
    hra
    -0.69
    gian
    -0.68
    inen
    -0.68
    ocr
    -0.68
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.67
    POSITIVE LOGITS
     relocation
    1.25
     relocated
    1.08
     relocate
    1.03
     unemploy
    0.82
     hous
    0.76
    pora
    0.72
    itory
    0.71
     eviction
    0.70
     displaced
    0.69
    opolis
    0.69
    Act Density 0.007%

    No Known Activations