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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal issues and societal obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.79
    IsMutable
    -0.72
    FormTagHelper
    -0.61
     coel
    -0.61
     HasFactory
    -0.59
    vician
    -0.59
    ⓧ
    -0.59
    XtraEditors
    -0.59
     يتيمه
    -0.57
    expandindo
    -0.56
    POSITIVE LOGITS
     withal
    1.10
     ifrån
    0.61
    énario
    0.60
    +#+
    0.53
     إليها
    0.52
     upon
    0.50
     עליו
    0.47
     إليه
    0.46
    ťaž
    0.44
     too
    0.44
    Act Density 0.158%

    No Known Activations