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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing completion or readiness

    oai_token-act-pair · gpt-3.5-turbo

    connecting words and phrases, particularly conjunctions and transitional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thur
    -0.63
    devices
    -0.63
    pora
    -0.61
     TM
    -0.61
     synonymous
    -0.59
     thor
    -0.58
    acho
    -0.58
    Jump
    -0.58
     veins
    -0.58
     Transactions
    -0.57
    POSITIVE LOGITS
    nered
    0.86
    dden
    0.78
    ersed
    0.77
    ubric
    0.76
    itud
    0.75
    structed
    0.73
    gre
    0.73
    rand
    0.71
    ured
    0.69
    owship
    0.68
    Act Density 0.099%

    No Known Activations