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

    Neuronpedia

    INDEX
    Explanations

    data structures and their definitions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused8>
    -0.84
    <unused52>
    -0.84
    <unused41>
    -0.84
    <unused51>
    -0.84
    <unused43>
    -0.84
    <unused42>
    -0.84
    <unused47>
    -0.84
    <unused74>
    -0.84
    <unused23>
    -0.84
    <unused28>
    -0.84
    POSITIVE LOGITS
     of
    0.29
     iVar
    0.27
     обслуживания
    0.24
    .
    0.24
     g
    0.23
    toBe
    0.23
     bVar
    0.22
     bri
    0.21
    g
    0.21
    A
    0.21
    Act Density 0.007%

    No Known Activations