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

    Neuronpedia

    INDEX
    Explanations

    independent clauses with specific grammatical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.76
    VERTISEMENT
    -0.74
    Portály
    -0.74
    mybatisplus
    -0.73
    ChildScrollView
    -0.73
    Datuak
    -0.72
    DockStyle
    -0.71
     Rptr
    -0.71
    databind
    -0.70
     GenerationType
    -0.70
    POSITIVE LOGITS
    ↵
    1.04
    ↵↵
    0.95
    [toxicity=0]
    0.92
    ↵↵↵
    0.90
    })));
    0.85
    ↵↵↵↵
    0.85
    ↵↵↵↵↵
    0.78
    ↵↵↵↵↵↵
    0.77
    <blockquote>
    0.71
    }},
    0.70
    Act Density 0.005%

    No Known Activations