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

    Neuronpedia

    INDEX
    Explanations

    timestamp formats in structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.81
    ſelf
    -0.79
    ſelves
    -0.79
     purpoſe
    -0.78
     whoſe
    -0.77
     myſelf
    -0.76
     chofe
    -0.75
     greateſt
    -0.75
     resourceCulture
    -0.75
     photolibrary
    -0.74
    POSITIVE LOGITS
    :
    0.63
    cy
    0.46
    エイ
    0.45
     hele
    0.45
    伊
    0.45
    rep
    0.45
    кор
    0.45
    aj
    0.44
    setopt
    0.44
    run
    0.44
    Act Density 0.153%

    No Known Activations