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

    Neuronpedia

    INDEX
    Explanations

    concepts related to justice and ethical decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    livan
    -0.54
    InjectAttribute
    -0.52
     virtuel
    -0.49
    turned
    -0.49
    leet
    -0.48
    <bos>
    -0.48
     naselje
    -0.47
    간
    -0.47
    ampung
    -0.47
    intar
    -0.47
    POSITIVE LOGITS
    enterOuterAlt
    0.81
    DockStyle
    0.79
    脚注の使い方
    0.77
     toimi
    0.71
    __":
    0.71
     choice
    0.69
     MainAxisSize
    0.67
    __':
    0.61
    RegistryLite
    0.61
    цуз
    0.60
    Act Density 0.265%

    No Known Activations