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

    Neuronpedia

    INDEX
    Explanations

    descriptions of personal background and experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.59
    "}
    -0.56
    mpire
    -0.54
    continental
    -0.53
    ssl
    -0.53
    ê
    -0.52
    apper
    -0.52
    donald
    -0.52
    Untitled
    -0.51
    alist
    -0.51
    POSITIVE LOGITS
     however
    0.86
     therefore
    0.76
     moreover
    0.70
     furthermore
    0.64
     also
    0.63
     meanwhile
    0.58
     certainly
    0.56
     though
    0.53
     ital
    0.53
    olars
    0.53
    Act Density 1.233%

    No Known Activations