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

    Neuronpedia

    INDEX
    Explanations

    words and phrases conveying complexity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     אחרים
    -0.52
    adaptiveStyles
    -0.50
    Przypisy
    -0.47
     hidup
    -0.47
    """,
    -0.46
    Kjelder
    -0.46
     które
    -0.46
    rzez
    -0.45
    karena
    -0.45
     που
    -0.44
    POSITIVE LOGITS
     very
    0.79
    ingly
    0.78
     Administrativna
    0.74
     تانيه
    0.72
    Aiheesta
    0.71
     intptr
    0.70
     singuli
    0.69
     décédé
    0.67
     considerable
    0.65
     decidedly
    0.64
    Act Density 0.178%

    No Known Activations