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

    Neuronpedia

    INDEX
    Explanations

    references to a specific code or label related to a dataset, particularly in the context of experiments or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.89
     myſelf
    -1.74
    ſelf
    -1.66
     ſeveral
    -1.63
     itſelf
    -1.61
    ſelves
    -1.57
     ſtate
    -1.55
     themſelves
    -1.54
     Houſe
    -1.52
     houſe
    -1.52
    POSITIVE LOGITS
     ver
    1.05
    ver
    1.01
     Die
    0.90
     die
    0.85
    ute
    0.84
     Ver
    0.83
    Ver
    0.80
    Die
    0.80
     den
    0.76
     Das
    0.71
    Act Density 0.130%

    No Known Activations