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

    Neuronpedia

    INDEX
    Explanations

    abbreviated references to scientific publications and their authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.57
     autorytatywna
    -0.53
    UnsafeEnabled
    -0.48
     endwhile
    -0.45
    
    -0.45
     stond
    -0.43
    destroyAll
    -0.43
    cosis
    -0.43
     punctuation
    -0.43
     saites
    -0.42
    POSITIVE LOGITS
    "]);
    0.88
     سكانية
    0.81
     Italijani
    0.71
    lapsingToolbar
    0.68
    )";
    0.68
    )");
    0.66
    "]];
    0.66
    writeFieldEnd
    0.66
    — 
    0.65
    AsUp
    0.65
    Act Density 0.324%

    No Known Activations