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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the substring "ak" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingham
    -0.93
     Accountability
    -0.67
    builders
    -0.66
    bury
    -0.64
     Walls
    -0.63
    enegger
    -0.63
    ãĤ£
    -0.63
    feeding
    -0.62
     Stim
    -0.61
     laureate
    -0.61
    POSITIVE LOGITS
    ansas
    0.84
    AY
    0.84
    rily
    0.81
    umar
    0.80
    ANE
    0.80
    ril
    0.79
    ernels
    0.78
    orea
    0.76
    lein
    0.76
    atana
    0.74
    Act Density 0.008%

    No Known Activations