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

    Neuronpedia

    INDEX
    Explanations

    historical facts or references

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical and organizational references, particularly in sports, politics, and societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LET
    -0.74
    MAL
    -0.73
    Ô
    -0.73
    Cause
    -0.63
    ERG
    -0.63
    ORS
    -0.61
    UCT
    -0.60
    Flag
    -0.60
    Scan
    -0.59
     unnecess
    -0.59
    POSITIVE LOGITS
     fame
    1.07
     Nanto
    0.74
     who
    0.73
     whose
    0.72
    whose
    0.71
     nicknamed
    0.69
     whom
    0.66
    hid
    0.63
    quartered
    0.63
     recruited
    0.62
    Act Density 0.624%

    No Known Activations