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

    Neuronpedia

    INDEX
    Explanations

    emphasis on the existence or presence of something significant or noteworthy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.95
     autorytatywna
    -0.94
     houſe
    -0.94
     Roskov
    -0.92
    -0.92
    GEBURTSDATUM
    -0.89
     Houſe
    -0.89
     Cæsar
    -0.89
     Վերցված
    -0.87
    Попис
    -0.85
    POSITIVE LOGITS
    ']}
    0.69
    Theres
    0.67
     theres
    0.65
     Theres
    0.64
     Ways
    0.64
     plenty
    0.63
    enc
    0.60
     a
    0.59
    vid
    0.59
    theres
    0.58
    Act Density 0.128%

    No Known Activations