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

    Neuronpedia

    INDEX
    Explanations

    numerical values and quantifiable measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     massively
    -0.63
    +#+#
    -0.57
    #+#
    -0.56
     quasi
    -0.55
     meaningful
    -0.54
     meaningfully
    -0.54
     relevant
    -0.53
     ví
    -0.52
     low
    -0.51
    usty
    -0.51
    POSITIVE LOGITS
    Спољашње
    0.68
    IntoConstraints
    0.66
     enfans
    0.64
     fuite
    0.63
     disparu
    0.62
     hennes
    0.62
     dagens
    0.60
     dépens
    0.60
     rechange
    0.59
     étoient
    0.59
    Act Density 1.575%

    No Known Activations