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

    Neuronpedia

    INDEX
    Explanations

    words containing the string "wan" with varying activations

    oai_token-act-pair · gpt-3.5-turbo

    the name "Marwan" appearing multiple times in relation to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     predictive
    -0.72
     leaflets
    -0.71
    £ı
    -0.69
    ttle
    -0.69
     clustered
    -0.68
    igslist
    -0.65
     liability
    -0.65
     practicable
    -0.65
     Gemini
    -0.64
    İĭ
    -0.63
    POSITIVE LOGITS
    wan
    1.24
    athan
    1.08
    igan
    1.06
    igans
    1.05
    wu
    1.04
    ovan
    0.99
    hao
    0.98
    nee
    0.97
    awan
    0.97
     Kenobi
    0.95
    Act Density 0.007%

    No Known Activations