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

    Neuronpedia

    INDEX
    Explanations

    references to coding or programming activities

    oai_token-act-pair · gpt-3.5-turbo

    references to coding and programming activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blooming
    -0.72
    Mobil
    -0.72
    Ĥİ
    -0.71
     Mutual
    -0.71
    toggle
    -0.70
     Somers
    -0.70
     Limbaugh
    -0.69
     Vaugh
    -0.68
     istg
    -0.68
    esville
    -0.67
    POSITIVE LOGITS
     coding
    0.99
     coded
    0.83
    oding
    0.83
    oded
    0.78
     codes
    0.76
    ode
    0.76
     cod
    0.75
     chops
    0.74
     genius
    0.72
    urally
    0.71
    Act Density 0.013%

    No Known Activations