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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate something being acknowledged or recognized as significant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     justice
    -0.47
     du
    -0.46
     de
    -0.45
     os
    -0.45
     dis
    -0.44
     und
    -0.44
     ge
    -0.43
     nervous
    -0.43
     por
    -0.43
     the
    -0.43
    POSITIVE LOGITS
    known
    0.94
     known
    0.86
     znám
    0.85
     Known
    0.84
    Known
    0.83
     conocida
    0.83
     conocido
    0.82
     increí
    0.82
     conocidos
    0.81
     kjent
    0.80
    Act Density 0.272%

    No Known Activations