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

    Neuronpedia

    INDEX
    Explanations

    words related to electrical circuits

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "circuit."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipple
    -0.73
    ACTED
    -0.73
    minster
    -0.69
    spell
    -0.66
    token
    -0.66
    sson
    -0.64
    umar
    -0.62
    cott
    -0.61
    terday
    -0.60
     Lak
    -0.60
    POSITIVE LOGITS
     breaker
    1.14
    cles
    0.80
     circuits
    0.79
    eer
    0.78
    eering
    0.77
    engers
    0.77
    ously
    0.75
     Breaker
    0.74
    ous
    0.73
     overse
    0.73
    Act Density 0.030%

    No Known Activations