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

    Neuronpedia

    INDEX
    Explanations

    references to seeds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ())))
    -0.44
    }]
    -0.42
    原始内容存档于
    -0.42
     measured
    -0.42
    ]}>
    -0.41
     demonstrated
    -0.41
    "]/
    -0.40
    ")))
    -0.40
    ?>
    -0.40
    ]/
    -0.40
    POSITIVE LOGITS
    istoitu
    0.68
    enterOuterAlt
    0.58
     betweenstory
    0.57
    ThroughAttribute
    0.56
    expandindo
    0.56
    EndGlobalSection
    0.56
    Industrial
    0.55
     ProtoMessage
    0.55
    endregion
    0.54
    IsMutable
    0.54
    Act Density 0.458%

    No Known Activations