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

    Neuronpedia

    INDEX
    Explanations

    references to the town of Goshen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words starting gos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Locke
    -0.57
    RTLR
    -0.56
    atase
    -0.56
     ModelRenderer
    -0.53
    Montana
    -0.52
    weber
    -0.51
    \"");
    -0.51
    Cali
    -0.51
    Michigan
    -0.51
    }")]
    -0.51
    POSITIVE LOGITS
     Gos
    2.59
    Gos
    2.36
     gos
    1.91
    gos
    1.55
     GOS
    1.52
    GOS
    1.27
     Gosling
    1.14
     Gost
    0.84
     gospod
    0.82
     Goss
    0.80
    Act Density 0.003%

    No Known Activations