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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "supports" and its variations

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

    supports what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]++;
    -0.53
    <bos>
    -0.46
    ]--;
    -0.44
    }}}}
    -0.42
     }}}
    -0.41
     Sales
    -0.40
     SALES
    -0.40
    Biografie
    -0.38
    Sales
    -0.38
     fame
    -0.37
    POSITIVE LOGITS
    Supports
    1.31
     Supports
    1.31
     supports
    1.24
    supports
    1.23
    adaptiveStyles
    0.72
     Supported
    0.71
    Supported
    0.70
    supported
    0.69
     opposes
    0.64
     supported
    0.64
    Act Density 0.017%

    No Known Activations