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

    Neuronpedia

    INDEX
    Explanations

    phrases related to returning or going home

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "home."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "]=>
    -0.82
    umbers
    -0.68
     gau
    -0.65
     gauge
    -0.64
    ickr
    -0.64
    immers
    -0.64
    yz
    -0.62
    amen
    -0.61
    enance
    -0.61
    ggles
    -0.60
    POSITIVE LOGITS
     safely
    0.90
    ported
    0.77
    stairs
    0.77
    right
    0.75
    opath
    0.74
    rox
    0.74
    nikov
    0.73
    joy
    0.72
    rehend
    0.71
    stead
    0.70
    Act Density 0.022%

    No Known Activations