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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "home" is mentioned in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "home."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "]=>
    -0.83
    ickr
    -0.75
    =-=-=-=-=-=-=-=-
    -0.66
    ues
    -0.64
    uel
    -0.64
    immers
    -0.62
     odds
    -0.61
     gau
    -0.61
    yz
    -0.60
    uing
    -0.60
    POSITIVE LOGITS
    chool
    0.83
    home
    0.82
    ported
    0.79
    right
    0.78
    nikov
    0.77
    grown
    0.73
    court
    0.73
     safely
    0.73
    osponsors
    0.73
    earth
    0.72
    Act Density 0.027%

    No Known Activations