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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to systems and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    certainly
    -0.69
     certainly
    -0.69
     gärna
    -0.68
     probably
    -0.67
    ########.
    -0.65
    ngdoc
    -0.64
    must
    -0.64
    probably
    -0.64
     zullen
    -0.64
    may
    -0.63
    POSITIVE LOGITS
     exceeds
    0.85
     fails
    0.84
     proves
    0.72
    有任何
    0.69
    Fails
    0.66
    자가
    0.64
     fizer
    0.64
     exceed
    0.64
     prove
    0.64
     tiver
    0.63
    Act Density 0.615%

    No Known Activations