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

    Neuronpedia

    INDEX
    Explanations

    the word "nobody" within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "nobody" or the absence of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complete
    -0.71
    thus
    -0.68
    prem
    -0.66
     Lank
    -0.65
    anga
    -0.65
    etr
    -0.65
    church
    -0.64
    alam
    -0.64
    partial
    -0.63
    clus
    -0.62
    POSITIVE LOGITS
     else
    1.41
     dime
    0.90
    Else
    0.90
     Else
    0.89
    THING
    0.84
    zzle
    0.82
    soever
    0.79
     bothering
    0.78
     doubted
    0.78
     conceivable
    0.77
    Act Density 0.008%

    No Known Activations