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

    Neuronpedia

    INDEX
    Explanations

    dialogue quotes and questions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.76
    ftagPool
    -0.76
     мәкал
    -0.71
    setVerticalGroup
    -0.69
    ArrowToggle
    -0.68
    Portail
    -0.67
    StructEnd
    -0.67
    IntoConstraints
    -0.67
    下载附件
    -0.66
    SBATCH
    -0.65
    POSITIVE LOGITS
    __':
    0.46
    Unknown
    0.45
     unearthed
    0.44
    </tr>
    0.42
     unknown
    0.41
     [
    0.41
     Unknown
    0.40
    __':
    0.40
     unison
    0.39
     köz
    0.38
    Act Density 0.126%

    No Known Activations