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

    Neuronpedia

    INDEX
    Explanations

    words that emphasize literal situations or direct statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.73
    舺
    -0.67
     desmotivaciones
    -0.65
    niosek
    -0.64
     étoient
    -0.62
    rungsseite
    -0.62
     müſſen
    -0.61
     Infór
    -0.57
    ähteet
    -0.57
    seamnă
    -0.57
    POSITIVE LOGITS
     it
    0.59
     actual
    0.55
     One
    0.53
     the
    0.48
     The
    0.48
     World
    0.47
    Actual
    0.47
     Individual
    0.47
     It
    0.47
     New
    0.47
    Act Density 0.538%

    No Known Activations