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

    Neuronpedia

    INDEX
    Explanations

    locations or objects that have been left vacant or deserted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "abandoned" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.86
    thood
    -0.83
    ILA
    -0.80
    BIT
    -0.76
    aptic
    -0.76
    ansky
    -0.74
    lee
    -0.74
    aminer
    -0.73
    nesty
    -0.73
    abolic
    -0.72
    POSITIVE LOGITS
     wasteland
    0.99
     warehouse
    0.87
     mall
    0.86
     unfinished
    0.83
     remnants
    0.82
     ruins
    0.80
     dere
    0.78
     graveyard
    0.77
     storefront
    0.77
     buggy
    0.77
    Act Density 0.066%

    No Known Activations