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

    Neuronpedia

    INDEX
    Explanations

    numerical values in a structured format, particularly those related to measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and metrics related to data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bureaucr
    -0.60
     conce
    -0.59
    Recomm
    -0.53
     objection
    -0.53
     Salvation
    -0.51
     SCH
    -0.50
     Sher
    -0.50
    compan
    -0.49
     corpor
    -0.48
     SOC
    -0.48
    POSITIVE LOGITS
    milo
    0.81
    adeon
    0.74
    rican
    0.65
    pring
    0.64
    braska
    0.64
    umenthal
    0.64
    anye
    0.63
    anwhile
    0.62
    ifice
    0.62
    ulic
    0.61
    Act Density 0.440%

    No Known Activations