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

    Neuronpedia

    INDEX
    Explanations

    words related to computer programming and development

    oai_token-act-pair · gpt-3.5-turbo

    words or elements related to social media and online content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monstrous
    -0.80
     Ples
    -0.75
     whiff
    -0.73
     Canary
    -0.71
     CVE
    -0.68
     Rabb
    -0.65
     Clover
    -0.65
     scar
    -0.65
     refres
    -0.64
     Wol
    -0.63
    POSITIVE LOGITS
    arthed
    0.96
    metics
    0.91
    ition
    0.89
    Mo
    0.89
    ocity
    0.86
    Depth
    0.85
    ument
    0.83
    Ti
    0.82
    imore
    0.82
    acan
    0.82
    Act Density 0.153%

    No Known Activations