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

    Neuronpedia

    INDEX
    Explanations

    phrases related to high status or level of quality

    oai_token-act-pair · gpt-3.5-turbo

    words related to organization and efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pora
    -0.67
    thur
    -0.67
    UA
    -0.64
     TM
    -0.63
    uria
    -0.60
    VT
    -0.60
     Emblem
    -0.59
    atl
    -0.59
     Transactions
    -0.59
    DX
    -0.58
    POSITIVE LOGITS
    nered
    0.89
    structed
    0.78
    itud
    0.77
    ersed
    0.74
    gre
    0.74
    dden
    0.73
    ubric
    0.69
    gered
    0.66
    umenthal
    0.66
    rand
    0.65
    Act Density 0.099%

    No Known Activations