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

    Neuronpedia

    INDEX
    Explanations

    sections of scientific or technical content with high levels of detail

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portály
    -0.82
    ztály
    -0.82
     Mor
    -0.81
    ientôt
    -0.77
     Matth
    -0.77
    ThroughAttribute
    -0.76
     Morrison
    -0.75
    databind
    -0.74
    ressee
    -0.72
    มอ
    -0.71
    POSITIVE LOGITS
    ↵
    0.91
    [toxicity=0]
    0.80
    ↵↵
    0.79
    ↵↵↵
    0.77
    <blockquote>
    0.72
    ↵↵↵↵
    0.71
    ViewFeatures
    0.69
    }}],
    0.65
    }}}}
    0.63
     dianteira
    0.62
    Act Density 0.024%

    No Known Activations