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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to data structures and their analysis

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     po
    -0.52
    migrationBuilder
    -0.50
    Eligibility
    -0.50
     Everyone
    -0.49
     Po
    -0.48
     Co
    -0.47
    Everyone
    -0.47
     mix
    -0.46
     everyone
    -0.45
    $_['
    -0.45
    POSITIVE LOGITS
     Theſe
    0.90
     greateſt
    0.88
     purpoſe
    0.84
     ſtate
    0.84
     itſelf
    0.79
     themſelves
    0.79
     Conſ
    0.77
     Diſ
    0.75
     theſe
    0.75
     Jefus
    0.75
    Act Density 0.254%

    No Known Activations