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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Nobody"

    oai_token-act-pair · gpt-3.5-turbo

    the word "nobody" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complete
    -0.76
    thus
    -0.73
    tnc
    -0.71
    ean
    -0.68
    Gaza
    -0.68
    alam
    -0.67
    etr
    -0.67
     Lank
    -0.66
    uers
    -0.65
    prem
    -0.64
    POSITIVE LOGITS
     else
    1.46
     Else
    0.99
    Else
    0.98
     dime
    0.90
    THING
    0.87
    else
    0.83
     bothering
    0.82
     bom
    0.79
     cared
    0.78
     bothered
    0.78
    Act Density 0.013%

    No Known Activations