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

    Neuronpedia

    INDEX
    Explanations

    references to leadership or authority figures in challenging contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.69
    CodedInputStream
    -0.60
    InjectAttribute
    -0.59
     himſelf
    -0.57
    tagHelperRunner
    -0.56
    BeginContext
    -0.56
     protoimpl
    -0.56
     Reſ
    -0.56
     themſelves
    -0.56
     Theſe
    -0.56
    POSITIVE LOGITS
     yüzde
    0.61
    werp
    0.56
    æus
    0.55
    antMatchers
    0.52
    odenal
    0.52
    GEBURTSDATUM
    0.51
    twimg
    0.51
    verifyException
    0.51
    DrawerToggle
    0.51
    Πηγή
    0.50
    Act Density 0.170%

    No Known Activations