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

    Neuronpedia

    INDEX
    Explanations

    words related to database operations and information technology

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to various aspects of data and metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rabbit
    -0.69
     groom
    -0.64
     coax
    -0.63
     Emin
    -0.62
     Carrier
    -0.61
     shining
    -0.60
     Sever
    -0.59
     wired
    -0.59
     boil
    -0.59
     Welch
    -0.59
    POSITIVE LOGITS
    tions
    1.00
    lements
    0.93
    tion
    0.92
    uese
    0.91
    ement
    0.89
    mt
    0.83
    ption
    0.83
    oux
    0.82
    ng
    0.80
    ment
    0.80
    Act Density 0.267%

    No Known Activations